2023-03-19 18:00:00 +0000https://danromero.org/feed.xmlDan RomeroPersonal website of Dan RomeroRome, Sweet Rome meets ChatGPT<p>One of my <a href="https://www.reddit.com/r/AskReddit/comments/k067x/comment/c2giwm4/">favorite reddit threads</a> is a story that became known as <a href="https://en.wikipedia.org/wiki/Rome,_Sweet_Rome">Rome, Sweet Rome</a>. The author was able to get the reddt posts optioned into a movie, but it’s been stuck in development hell for over a decade.</p>
<p>Wanting to try out ChatGPT 4, I took the premise from the Wikipedia page and had ChatGPT to start to write scenes for a potential screenplay. Bold text are my prompts.</p>
<hr />
<p><strong>Here’s the premise of a story:</strong></p>
<p><strong>The story is a fictional account of what might happen if a Marine Expeditionary Unit (MEU) of 2,200 men were to be somehow transported through time from their base in modern-day Kabul, Afghanistan to the time of the Roman Empire when being ruled by Augustus Caesar, appearing near the Tiber River in 23 BC with their full allotment of equipment - M1 Abrams battle tanks, bulletproof vests, M249 SAW light machine guns, M16A4 rifles, and grenades, but with no way to resupply with fuel or ammunition when depleted.</strong></p>
<p><strong>We fast forward to the camp of the MEU. Come up with names for the characters (with accurate military titles) and how are they thinking about next steps. The new piece of information is there’s a Roman army of 5,000 men 10 miles up the road setting up camp. Write in the style of a screenplay.</strong></p>
<p>FADE IN:</p>
<p>EXT. MARINE EXPEDITIONARY UNIT CAMP - DAY</p>
<p>We see the camp of the MEU, a bustling scene of military activity. Marines are cleaning weapons, repairing vehicles, and engaging in physical training. Suddenly, a group of Marines approach a command tent.</p>
<p>INT. COMMAND TENT - DAY</p>
<p>The group consists of Lieutenant Colonel John Smith, Major Rachel Johnson, and Sergeant First Class David Rodriguez.</p>
<p>LT. COL. SMITH
(looking at a map)
Alright, we’ve been here for a few days now and we’ve assessed our situation. We’ve got 2,200 Marines, a full complement of equipment, and no way to resupply.</p>
<p>MAJ. JOHNSON
(nodding)
That’s right. And now we’ve got a Roman army setting up camp 10 miles up the road.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(grimacing)
And we can’t resupply our weapons or vehicles when we run out of ammo or fuel.</p>
<p>LT. COL. SMITH
(pacing)
We’ve got to think strategically here. We’ve got an advantage with our equipment, but we’re vastly outnumbered.</p>
<p>MAJ. JOHNSON
(thoughtful)
Perhaps we could use a small team to scout out the Roman camp, gather intelligence, and see if we can find any weaknesses.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(excited)
Yeah, and maybe we could use our tanks to break through their lines and cause chaos.</p>
<p>LT. COL. SMITH
(shaking his head)
We can’t just charge in blindly. We need a plan.</p>
<p>MAJ. JOHNSON
(nodding)
I agree. Let’s take the next few hours to come up with a detailed plan of action. We need to use our resources wisely and stay one step ahead of the Romans.</p>
<p>LT. COL. SMITH
(grim determination)
Agreed. We’re Marines. We adapt and overcome. Let’s get to work.</p>
<p>The three of them exit the tent, ready to face whatever challenges lay ahead.</p>
<p>FADE OUT.</p>
<p><strong>Write a scene where the MEU comes up with a clever plan to outsmart the Romans. Remember they are out numbered and while they have modern weapons, have a finite amount of ammunition, fuel, etc.</strong></p>
<p>FADE IN:</p>
<p>INT. COMMAND TENT - DAY</p>
<p>Lieutenant Colonel John Smith, Major Rachel Johnson, and Sergeant First Class David Rodriguez sit around a table, poring over a map of the surrounding area.</p>
<p>LT. COL. SMITH
(looking up from the map)
Alright, we’ve got a plan.</p>
<p>MAJ. JOHNSON
(excitedly)
Let’s hear it.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(leaning forward)
Yeah, what’s the play?</p>
<p>LT. COL. SMITH
(smiling)
We’re going to use our tanks and infantry to set up a fake roadblock and draw the Roman army in.</p>
<p>MAJ. JOHNSON
(raising an eyebrow)
And then what?</p>
<p>LT. COL. SMITH
(leaning in)
We’ll use our tanks to create a gap in their lines and then send in our infantry to flank them from the sides.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(nodding)
That could work. But what about our limited ammo and fuel?</p>
<p>LT. COL. SMITH
(grinning)
That’s where the fake roadblock comes in. We’ll have our engineers rig up some dummy tanks and other equipment to make it look like we have a much larger force than we actually do. We’ll keep our real tanks and heavy weapons hidden until the Romans are in position, and then we’ll hit them hard and fast.</p>
<p>MAJ. JOHNSON
(impressed)
That’s clever. But what about their cavalry?</p>
<p>LT. COL. SMITH
(thoughtful)
We’ll have to take them out early. Our snipers and anti-tank weapons should be able to do the trick.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(smiling)
Alright, sir. Let’s get to it.</p>
<p>The three of them stand up and head out of the tent to begin preparations.</p>
<p>FADE OUT.</p>
<p>FADE IN:</p>
<p>EXT. BATTLEFIELD - DAY</p>
<p>The MEU is in position, with their tanks and infantry hidden behind a hill. The fake roadblock is set up, with dummy tanks and other equipment on display.</p>
<p>A scout reports back that the Roman army is approaching.</p>
<p>LT. COL. SMITH
(grinning)
Alright, let’s put our plan into action.</p>
<p>The Marines man their positions, with snipers and anti-tank weapons in position to take out the Roman cavalry.</p>
<p>As the Romans approach the roadblock, the Marines open fire. The Roman army charges forward, falling right into the trap.</p>
<p>The MEU’s tanks move forward, firing on the Romans and creating a gap in their lines. The Marines pour through the gap, flanking the Romans from the sides.</p>
<p>The battle is intense, with both sides taking heavy losses. But the MEU’s superior equipment and tactics begin to turn the tide.</p>
<p>Finally, the Romans break and begin to retreat.</p>
<p>LT. COL. SMITH
(smiling)
Alright, let’s not let them get away. Pursue them and mop up any survivors.</p>
<p>The MEU’s tanks and infantry chase down the fleeing Romans, taking out stragglers and securing the battlefield.</p>
<p>FADE OUT.</p>
<p>FADE IN:</p>
<p>EXT. BATTLEFIELD - LATER</p>
<p>The MEU stands victorious, with the Roman army defeated and scattered.</p>
<p>LT. COL. SMITH
(addressing the Marines)
Well done, Marines. You adapted to a difficult situation and came out on top.</p>
<p>MAJ. JOHNSON
(nodding)
But let’s not forget that we’re still stranded in the past, with limited resources.</p>
<p>SGT. 1ST CLASS RODRIGUEZ
(smiling)
But at least we know we can</p>
<p><strong>Write a scene where Caesar is processing the massive defeat to this strange enemy with extremely powerful and strange weapons. Remember he does not know what Marines or guns or tanks are. But Caesar is also not histrionic and thinking these are “gods”. He’s particularly focused on next steps and how he can learn more about this strange enemy force.</strong></p>
<p>FADE IN:</p>
<p>INT. CAESAR’S TENT - DAY</p>
<p>Caesar sits at a table, his head in his hands. His advisers are gathered around him, looking worried.</p>
<p>ADVISER 1
(worriedly)
My lord, the reports are coming in. The enemy has decimated our army.</p>
<p>ADVISER 2
(shocked)
Their weapons… they are like nothing we have ever seen before.</p>
<p>CAESAR
(looking up)
I know. It’s like they are from another world.</p>
<p>ADVISER 3
(puzzled)
What do you mean, my lord?</p>
<p>CAESAR
(thoughtful)
I mean that their weapons and tactics are so different from anything we know. It’s like they are using magic.</p>
<p>ADVISER 1
(shaking his head)
But my lord, they are just men like us. They must have some kind of weakness.</p>
<p>CAESAR
(nodding)
You’re right. We need to learn more about them, so we can find their weaknesses and defeat them.</p>
<p>ADVISER 2
(curious)
How do you propose we do that, my lord?</p>
<p>CAESAR
(determined)
We’ll send scouts to observe their movements and gather intelligence. We need to know everything about them, from their weapons to their tactics to their leadership.</p>
<p>ADVISER 3
(nodding)
And then what, my lord?</p>
<p>CAESAR
(thoughtful)
We’ll use that intelligence to plan our next move. We’ll find a way to counter their weapons and use our superior numbers to defeat them.</p>
<p>ADVISER 1
(optimistic)
We can do it, my lord. We have defeated powerful enemies before.</p>
<p>CAESAR
(smiling)
That’s right. We are the Romans. We do not give up in the face of adversity.</p>
<p>ADVISER 2
(excitedly)
My lord, we must also consider the possibility that they are not alone. They could have allies or even more powerful weapons.</p>
<p>CAESAR
(nodding)
That’s true. We need to be prepared for anything.</p>
<p>ADVISER 3
(respectfully)
My lord, you always find a way to triumph over your enemies. I have no doubt that we will prevail in this war.</p>
<p>CAESAR
(smiling)
Thank you, my friend. But we must also remember that this is not just about victory. It’s about defending Rome and our way of life from those who seek to destroy it.</p>
<p>The advisers nod in agreement, as Caesar stands up and heads out of the tent, ready to face the challenges ahead.</p>
<p>FADE OUT.</p>
<p><strong>Write a scene in the Roman Senate where senators who dislike Caesar are hearing about the results of the catastrophic defeat to a strange and powerful enemy. Assume these Senators think this could be an opportunity to get rid of Caesar.</strong></p>
<p>FADE IN:</p>
<p>INT. ROMAN SENATE - DAY</p>
<p>A group of senators are gathered in the Senate chamber, whispering amongst themselves. They are all worried about the news of the defeat to the strange and powerful enemy.</p>
<p>SENATOR 1
(angrily)
This is a disaster. How could Caesar let this happen?</p>
<p>SENATOR 2
(nodding)
He’s been too focused on his own ambitions and not on the safety of Rome.</p>
<p>SENATOR 3
(sneering)
Perhaps this is an opportunity for us to finally get rid of him.</p>
<p>SENATOR 1
(interested)
What do you mean?</p>
<p>SENATOR 3
(smiling)
Think about it. This defeat is a stain on Caesar’s record. If we can make it look like he was responsible for it, the people will turn against him.</p>
<p>SENATOR 2
(skeptical)
But how do we make it look like he’s responsible?</p>
<p>SENATOR 3
(slyly)
We spread rumors. We tell the people that Caesar was too proud to listen to the advice of his advisers. We make it look like he was overconfident and foolish.</p>
<p>SENATOR 1
(nodding)
And then what?</p>
<p>SENATOR 3
(grinning)
We call for a vote of no confidence in Caesar. We get the people and the Senate to turn against him, and then we can take control of Rome ourselves.</p>
<p>SENATOR 2
(uneasy)
But won’t this be risky? What if Caesar finds out what we’re planning?</p>
<p>SENATOR 3
(confidently)
He won’t. We’ll be subtle. We’ll plant the seeds of doubt in the minds of the people and let them do the rest.</p>
<p>The other senators nod, impressed by Senator 3’s plan.</p>
<p>SENATOR 1
(resolutely)
Alright, let’s do it. We’ll start spreading the rumors and see where it leads.</p>
<p>The senators stand up, ready to put their plan into action.</p>
<p>FADE OUT.</p>
<p><strong>Write a scene where a Roman scout is able to sneak up on a MEU guard and capture him, including his rifle.</strong></p>
<p>FADE IN:</p>
<p>EXT. MEU CAMP - NIGHT</p>
<p>A Roman scout, dressed in dark clothing and carrying a sword, moves silently through the darkness. He approaches a Marine guard, who is standing watch with his M16A4 rifle at the ready.</p>
<p>The Marine, unaware of the scout’s presence, turns his head for a moment, scanning the horizon.</p>
<p>The scout sees his opportunity and moves quickly, leaping forward and grabbing the Marine from behind. The Marine struggles, but the scout is too quick and too strong.</p>
<p>He disarms the Marine, taking his rifle and tossing it aside. He then binds the Marine’s hands and drags him away from the camp.</p>
<p>FADE OUT.</p>
<p><strong>Write the scene where Caesar is presented with the MEU guard as a prisoner but also is able to inspect his rifle. He accidentally pulls the trigger and it kills a Roman guard. While everyone is frightened, Caesar realizes what this new technology could be.</strong></p>
<p>FADE IN:</p>
<p>INT. CAESAR’S TENT - DAY</p>
<p>A group of Roman soldiers, led by the scout who captured the Marine guard, present the prisoner to Caesar.</p>
<p>The Marine guard is dirty and disheveled, with his hands bound behind his back. He looks up at Caesar, who stares back at him coldly.</p>
<p>CAESAR
(to the scout)
What is the meaning of this?</p>
<p>SCOUT
(respectfully)
My lord, we captured this man from the enemy camp.</p>
<p>Caesar nods, then turns his attention to the prisoner.</p>
<p>CAESAR
(angrily)
Who are you? What is your purpose here?</p>
<p>MARINE GUARD
(defiantly)
I am a Marine, a soldier of the United States.</p>
<p>Caesar looks confused.</p>
<p>CAESAR
(looking to his advisers)
What is a “United States”?</p>
<p>ADVISER 1
(puzzled)
We do not know, my lord. Perhaps it is the name of their leader.</p>
<p>ADVISER 2
(cautiously)
My lord, we should be careful. This enemy has weapons we have never seen before.</p>
<p>As Caesar examines the prisoner, his eyes fall on the Marine’s rifle, which has been placed on a nearby table.</p>
<p>CAESAR
(curiously)
What is this?</p>
<p>The scout steps forward and picks up the rifle, handing it to Caesar.</p>
<p>SCOUT
(respectfully)
My lord, it is one of their weapons. It is said to be very powerful.</p>
<p>Caesar examines the rifle, turning it over in his hands. He sees the trigger and, out of curiosity, pulls it.</p>
<p>There is a loud bang, and a Roman guard standing nearby falls to the ground, clutching his chest.</p>
<p>The room erupts in chaos as soldiers rush to the guard’s aid.</p>
<p>CAESAR
(shocked)
What… what just happened?</p>
<p>ADVISER 1
(trembling)
My lord, it seems the weapon is designed to fire a projectile with great force.</p>
<p>ADVISER 2
(alarmed)
It’s like nothing we’ve ever seen before. It could revolutionize warfare.</p>
<p>CAESAR
(looking at the rifle)
This changes everything. We need to learn more about these weapons, and the people who use them.</p>
<p>The advisers nod in agreement, as Caesar turns his attention back to the Marine guard.</p>
<p>CAESAR
(to the guard)
You will tell us everything you know about these weapons and your people.</p>
<p>The Marine guard looks up at Caesar, his expression defiant.</p>
<p>MARINE GUARD
(resolutely)
I will tell you nothing.</p>
<p>Caesar nods, then turns to the scout.</p>
<p>CAESAR
(to the scout)
Take him away. We will find a way to make him talk.</p>
<p>The scout nods, and he and his soldiers lead the prisoner away.</p>
<p>FADE OUT.</p>
Sun, 19 Mar 2023 18:00:00 +0000Sun, 19 Mar 2023 18:00:00 +0000https://danromero.org/rome-sweet-rome-chatgpt.htmlDan RomeroHaving ChatGPT draft a screenplay for Rome, Sweet, Rome.Farcaster ideas<p>Lightly edited, please excuse typos. No guarantee these ideas are any good and/or viable businesses. Ask me clarifying questions on Farcaster.</p>
<ol>
<li>Friends iMessage UI — make a client that looks like the iMessage home screen UI; if someone you’re following casts, bump them to the top of the list; eventually allow pinning people</li>
<li>Groups — allow someone to start a public group by mentioning the other members in the initial cast.</li>
<li>Photo only — Glass but for Farcaster</li>
<li>Video only auto play — TikTok for Farcaster</li>
<li>Podcast — surface all podcast links shared on Farcaster / but also map Farcasters <> podcasts they produce a la alias.co; ability to listen in feed; like a podcast episode or a timestamp and auto-cast that your primary Farcaster protocol feed</li>
<li>Links — surface all URLs shared on Farcaster / but also map Farcaster blogs / Substack / Mirror / Paragraphs / etc.</li>
<li>Q & A — show all top-level question casts with a bunch of replies</li>
<li>Bookmark organization and search — perl (rip) had a dedicated user base; figure out what people liked about it and expand from there</li>
<li>Simple ticket system for Farcaster meet ups and events — come up with a QR code / JSON format that allows an event organizer and an attendee to do a double opt-in sign</li>
<li>Token-gated client — only show casts / reactions from users with a given on-chain thing (NFT, characteristic); important: casts will still be public on the protocol, but when using this client you get to pretend everyone else doesn’t exist</li>
<li>NBAcaster — do an open edition for people interested in NBA on Farcaster, build a token-gated client for it; incorporate NBA gifs, memes, scores, etc.</li>
<li>F1caster — same idea as above but for F1</li>
<li>Parentcaster - do an open edition for people with kids Farcaster, build a token-gated client for it</li>
<li>Musicaster - do an open edition for people who like sharing / discovering music on Farcaster, build a token-gated client for it; in-feed listening to spotify, soundcloud, youtube, music nfts</li>
<li>All In Caster — a client that acts as a sort of virtual book club for the All In podcast. Borrrow from the podcast client idea, esp. with timestamps and NBA caster</li>
<li>Back up all cast data paid service — dev tool for power users or other clients, but automatically back up all your Farcaster protocol data for archival purposes</li>
<li>FarHouse — Clubhouse + <a href="http://daily.co">daily.co</a> audio SDK + Farcaster</li>
<li>Hub to Pipedream / Zapier — Pipedream already integrated to the Warpcast API, but create an open source library / paid service that pipes specific events from a Hub to no code / low code tools</li>
<li>Turntable / DJ / radio station — musicaster, but for virtual live music shows (kind of like a mellow version of Unlonely)</li>
<li>Stories — post a cast, automatically delete it 24 hours later</li>
<li>NFT masonry view — show all Farcaster protocol NFT mint / buy events in a masonry-</li>
<li>Context style feed / blockchain explorer — Context.app but for Farcaster users (i.e. a super-powered NFt feed)</li>
<li>Disqus style comments — what Paragraph does for it’s newsletters using casts as comments but for any blog</li>
<li>Check in app — old school Foursquare but on Farcaster (venue level granularity vs. city-level)</li>
<li>Recommendations app — subset of the Q/A app, but have a leaderboard with points for people who have the most / helpful recommendations</li>
<li>P2P payment app — open up to a Cash App-like send screen to generate a potential transaction to send to any Farcaster user — pushes the transaction into your default mobile Ethereum wallet</li>
<li>Goodreads — allow people to mark read / review books with a single cast</li>
<li>Hosted Hub — Offer hosted hubs for developers that don’t want to deal with infra</li>
<li>Meta client across all platforms — x-post / x-read with any social media platform with an open API</li>
<li>Oculus quest client — be early for when the Apple headset arrives and you’ve figured out cool stuff you can do with a feed in 3D space</li>
<li>iPad client — make a multi-column client for iPads</li>
<li>Windows app — make a desktop client for Windows</li>
<li>Tweetdeck multi column client — allow for users to customize what each column shows / filtering criteria for each column</li>
<li>People Directory — best place to search for and find people on Farcaster</li>
<li>Mint a cast</li>
<li>Support other blockchains like Bitcoin, Solana, Tezos</li>
<li>Show Twitter and Farcaster in the same feed (might need to get creative given API constraints; maybe scraping profiles)</li>
<li>Open source react native — start the open source react native mobile Farcaster client (a lot of the projects on this list would benefit)</li>
<li>Open source swift — start the open source native iOS Farcaster client</li>
<li>Open source flutter — another popular x-platform library</li>
<li>Create react app equivalent create Farcaster client — become the “hello world” go to for people starting out building a new farcaster client (could be web or could be react native )</li>
<li>Farcaster graph visualizer — social network analysis visualizations but Farcaster (using farcaster-py)</li>
<li>Etherscan but for Farcaster — keep super functional / minimal — anything on a Hub should have an atomic URL</li>
<li>Chrome extension that lets you like or comment any webpage and see other casters who have interacted with it — if you click the extension, you can type a comment, pushes out to Farcaster feeds with a link, but if you visit a page that’s already been commented on</li>
<li>Chrome extension that replaces Twitter sidebar with Farcaster like twemex</li>
<li>Display Farcaster link and profile for any user on Twitter — like Hive One extension does</li>
<li>Dev call OpenAI whisper auto transcriptions</li>
<li>Hub explorer - how many hubs are running etc</li>
<li>Open source Hub to Postgres adapter</li>
<li>ActivityPub bridge — run <a href="http://casterdon.social">casterdon.social</a> - every Farcaster user automatically has an account on the Mastodon server and their casts are cross posted; would pair nicely with a meta social network client</li>
</ol>
Mon, 06 Mar 2023 18:00:00 +0000Mon, 06 Mar 2023 18:00:00 +0000https://danromero.org/farcaster-ideas.htmlDan RomeroIdeas for stuff to build on Farcaster.On subscriptions<p>Most consumer apps during the 2010s monetized with free with ads model because:</p>
<ol>
<li>Consumers weren’t paying for many online subscriptions (beyond an internet connection)</li>
<li>Google, and later Facebook, did so well with that model</li>
<li>Payments infra was bad (pre-Stripe, pre-Apple Pay and in-app subscriptions)</li>
<li>Zero-interest rates made capital relatively cheap and the market valued “growth and future profitability”</li>
</ol>
<p>Subscriptions seem to be growing in popularity in the 2020s:</p>
<ol>
<li>Consumers are savvier for a given category on whether they value free but time spent watching ads or paid with no ads, e.g. the success of streaming services like Netflix and Spotify shows there’s a big market here, esp. in developed countries. Amazon Prime is another example of a subscription that has, arguably, grown in value over time (started with free shipping, now video streaming, etc.)</li>
<li>Companies are realizing they don’t monetize as well as Google or Facebook (lack of scale, lack of in-house talent, etc.)</li>
<li>Infra to manage all of these subscriptions is better, i.e. managing all of your subscriptions through iOS is significantly better than “call this 1-800 number of this newspaper’s billing departtment to cancel” experience</li>
<li>Interest rates are back and markets seem to care about revenue, free cash flow, etc.</li>
</ol>
<p>Free with ads will likely always be a popular (if not the most popular) option for most Internet services. However, there’s an important shift that happens when you pay for something: you go from being a “user” to a “customer”. So rather than making product choices that optimize for “time spent” (which ultimately translates into ads viewed and revenue), you can make product choices that deliver “value” (measured through customer retention, churn, NPS, etc.). cf. “If you’re not paying for the product, you are the product.”</p>
Tue, 01 Nov 2022 18:00:00 +0000Tue, 01 Nov 2022 18:00:00 +0000https://danromero.org/on-subscriptions.htmlDan RomeroConsumer internet monetization in the 2010s vs. 2020sProduct-led protocol development<p>If your goal is to build a new protocol, start from the end goal—internet-scale protocol like DNS, HTTP, SMTP—and work backwards.</p>
<ol>
<li>
<p>A protocol is only as good as the number of independent and thriving clients, applications and businesses on it. A protocol with a lot of users but one dominant client is just an app with open APIs (for the time being). Practical alternative clients—not theoretical—matter for exit with interoperability.</p>
</li>
<li>
<p>Developers care far more about addressable quality daily active users (qDAUs) more than tech stack. A protocol with a lot of quality qDAUs and slightly worse technology will likely attract more developers than a protocol with better technology but few qDAUs. Quality defined as not bots or accounts that sign up and immediately churn (creating a ghost town effect).</p>
</li>
<li>
<p>Users don’t use protocols, they use apps. So if your goal is to build a protocol, you should build the initial app that’s high quality enough to earn the attention of enough qDAUs that developers start finding building on the protocol interesting.</p>
</li>
</ol>
<p>Lastly, it’s easy for people to fall into the Field of Dreams fallacy for protocols — “if you build it, they will come”. Can’t expect others to spend the time and effort to build high quality products if you’re not willing to do it yourself.</p>
Fri, 14 Oct 2022 18:00:00 +0000Fri, 14 Oct 2022 18:00:00 +0000https://danromero.org/product-led-protocols.htmlDan RomeroIf you're not willing to do it yourself, why would others?RSS+<p>I’ve mentioned <a href="https://danromero.org/farcaster/">before</a> that the original question we set out to answer when building Farcaster was how could you make RSS competitive with a public broadcast social network like Twitter. The initial name for the protocol was RSS+. Below is the original spec for the idea. People may find it helpful to see what questions we asked and tried to answer when starting out.</p>
<hr />
<h2 id="what-is-rss">What is RSS+?</h2>
<p>An enhancement to RSS which gives it a social graph and associated social actions. It’s a way to back into building a Twitter competitor. Solves for the <a href="https://www.google.com/url?q=https://platformed.info/seeding-two-sided-businesses-strategy-chicken-and-egg-problem/%23:~:text%3DThe%2520ghost%2520town%2520problem%2520(No%2520complementary%2520products)%26text%3DA%2520section%2520of%2520users%2520on,no%2520value%252C%2520in%2520the%2520platform.&sa=D&source=editors&ust=1662599945708327&usg=AOvVaw0Inp7q1FHgq6fhYydXmoKm">ghost town problem</a> by leveraging existing blogs that already have RSS feeds. Long-term, the graph likely lives on a blockchain to allow developers permissionless access to build a rich ecosystem of different clients, directories, block explorers and custom recommendation algorithms.</p>
<h2 id="premises">Premises</h2>
<ul>
<li>RSS is a <a href="https://www.google.com/url?q=https://en.wikipedia.org/wiki/Gunpei_Yokoi%23Lateral_Thinking_with_Withered_Technology&sa=D&source=editors&ust=1662599945708790&usg=AOvVaw34FBsEZOPbxKE1BG-_4JoD">withered technology</a>.</li>
<li>RSS is an information broadcast technology (like Twitter)</li>
<li>What killed RSS?
<ul>
<li>Technical / power user UX for infovores (journalists, investors, etc.)</li>
<li>Google launched the <a href="https://www.google.com/url?q=http://googlepress.blogspot.com/2005/10/google-reader_07.html&sa=D&source=editors&ust=1662599945709128&usg=AOvVaw0P9obCaWXQ5Mzwua9osfST">free Google Reader in 2005</a> and killed market independent RSS readers; better UX but still power user-focused</li>
<li>Twitter (2006) was a simpler UX and dramatically expanded the market for information broadcast</li>
<li>Why did Twitter succeed? mobile-friendly + follow model + discovery + information density (due to initial 140 character constraint) + feed to go during real-time (e.g. <a href="https://www.google.com/url?q=https://twitter.com/jkrums/status/1121915133&sa=D&source=editors&ust=1662599945709388&usg=AOvVaw1E2breP28pgQIxUHWqLO4u">plane in the Hudson</a>, <a href="https://www.google.com/url?q=https://twitter.com/ReallyVirtual/status/64783440226168832?ref_src%3Dtwsrc%255Etfw%257Ctwcamp%255Etweetembed%257Ctwterm%255E64783440226168832%257Ctwgr%255Eshare_3%252Ccontainerclick_0%26ref_url%3Dhttps%253A%252F%252Fwww.cnn.com%252F2016%252F01%252F20%252Fasia%252Fosama-bin-laden-raid-tweeter-sohaib-athar-rewind%252Findex.html&sa=D&source=editors&ust=1662599945709608&usg=AOvVaw2-07bSS3JY5-sAOPL64hNx">Osama bin Laden raid</a>)</li>
<li>Google abruptly shutting down Google Reader in <a href="https://www.google.com/url?q=https://googleblog.blogspot.com/2013/03/a-second-spring-of-cleaning.html&sa=D&source=editors&ust=1662599945709824&usg=AOvVaw2tIXwghbr_QNMLq-_YKisG">2013</a> led to most infovores to move 100% to Twitter</li>
<li>RSS is controlled by 1 person but has better branding than the consortium standard (Atom), cf. <a href="https://www.google.com/url?q=https://twobithistory.org/2018/12/18/rss.html&sa=D&source=editors&ust=1662599945710049&usg=AOvVaw2NNuHSfBjJWIZSfmqz0_Hz">The Rise and Demise of RSS</a> and <a href="https://www.google.com/url?q=https://danielmiessler.com/blog/atom-rss-why-we-should-just-call-them-feeds-instead-of-rss-feeds/&sa=D&source=editors&ust=1662599945710291&usg=AOvVaw0SjMr6J9xDLlnDtYcoOo02">Atom vs. RSS</a></li>
</ul>
</li>
<li>RSS ecosystem today is fragmented
<ul>
<li><a href="https://www.google.com/url?q=https://feedly.com/i/welcome&sa=D&source=editors&ust=1662599945710568&usg=AOvVaw0ABPwWvC-DocuHblD0r6XJ">Feedly</a> (VC-backed); <a href="https://www.google.com/url?q=https://www.wired.com/story/rss-readers-feedly-inoreader-old-reader/%23:~:text%3DWith%252014%2520million%2520users%252C%2520Feedly,RSS%2520reader%2520on%2520the%2520market.&sa=D&source=editors&ust=1662599945710774&usg=AOvVaw3lJkZBfOXeFYcn6aDY-UNy">14 million users in 2018</a></li>
<li><a href="https://www.google.com/url?q=https://feedbin.com/&sa=D&source=editors&ust=1662599945710948&usg=AOvVaw3tmHsQrYEmlFGhDPoLsPSm">Feedbin</a> (indie)</li>
<li>No clear winner as of November 2020</li>
</ul>
</li>
<li>Hiding in plain sight
<ul>
<li>Podcasts are a <a href="https://www.google.com/url?q=https://www.edisonresearch.com/infinite-dial-2019/&sa=D&source=editors&ust=1662599945711223&usg=AOvVaw3g_LU2H_R24b2j0euISiLh">growing category</a> powered entirely by <a href="https://www.google.com/url?q=https://itunespartner.apple.com/podcasts/articles/podcast-requirements-3058&sa=D&source=editors&ust=1662599945711379&usg=AOvVaw0rRUWLEzCtwyVy2L12dlnm">RSS</a>.</li>
<li>Substack newsletters all have an <a href="https://www.google.com/url?q=https://support.substack.com/hc/en-us/articles/360038239391-Is-there-an-RSS-feed-for-my-publication-&sa=D&source=editors&ust=1662599945711601&usg=AOvVaw0BEFy9UdmrYFPAgUhrt9y_">RSS feed</a>.</li>
</ul>
</li>
</ul>
<h2 id="what-constitutes-the-twitter-product-bundle">What constitutes the Twitter product bundle?</h2>
<ul>
<li>A post (tweet)</li>
<li>Namespace (@dwr)</li>
<li>1-click subscriptions (follows)</li>
<li>Discovery
<ul>
<li>Accounts
<ul>
<li>Who to follow lists</li>
<li>Search</li>
<li>via content</li>
</ul>
</li>
</ul>
</li>
<li>Content
<ul>
<li>Trending</li>
<li>Retweets</li>
<li>Algo feed via faves</li>
<li>Search</li>
</ul>
</li>
<li>Density due to (original) text-only UI and character limit constraint</li>
<li>Schelling point during real-time event or 24-hour news cycle (#hashtags illustrative but not necessary); the public square of the internet</li>
<li>DMs</li>
</ul>
<h2 id="mvp-decentralized-twitter-with-crypto">MVP decentralized Twitter (with crypto?)</h2>
<ul>
<li>Core actions relevant to the graph
<ul>
<li>Post</li>
<li>Follow</li>
<li>Unfollow</li>
<li>Like/Fave</li>
<li>Retweet</li>
</ul>
</li>
<li>Put on blockchain
<ul>
<li>Keep payload extremely small and solve blockchain scaling later – maybe content doesn’t need to last forever?
<ul>
<li>User name</li>
<li>Pointer to payload (hosted somewhere else like Github Pages, IPFS, etc. – this is key to avoid having to censor; maybe out of the box you can use the default client / hosting; key is exit)</li>
<li>Action</li>
<li>If to another user/piece of content (a fave, retweet, etc.)</li>
</ul>
</li>
<li>Leads to clients that are free but ad-supported or subscription clients</li>
<li>Allows for BYOC (bring your own client) and BYOA (bring your own algorithm)</li>
<li>Create reference directory like Coinmarketcap or block explorer like Etherscan (but others can create their own)</li>
<li>True ownership of namespace, content, graph</li>
<li>No censorship – can’t be evil</li>
<li>Spam problem solved? i.e. cheap enough for legit content producers and free to read but bot accounts are not worth money</li>
</ul>
</li>
<li>3rd party verification service (paid; could be the way for a potential company to monetize)
<ul>
<li>Why stop at just blue checks? Many different badges for verification!</li>
<li>Namespace mechanics like Handshake or Unstoppable domains</li>
<li>You have the right to sell your name via some DEX but the protocol gets a fee</li>
</ul>
</li>
</ul>
<h2 id="potential-starting-points">Potential starting points</h2>
<p>The bootstrapping problem here is a classic marketplace: supply (people who publish) and demand (people who read). In almost all cases (and especially early), people will be both. But long-term, the ecosystem will end up in a <a href="https://www.google.com/url?q=https://en.wikipedia.org/wiki/1%2525_rule_(Internet_culture)&sa=D&source=editors&ust=1662599945713995&usg=AOvVaw18_lWp8WEeg-6edruIE6VK">90/9/1 distribution</a>.</p>
<p>Usually, I would advise an entrepreneur to focus on high-quality supply—which tends to generate its own demand. In the case of RSS+, this would be about getting high-quality writers/thinkers (who are also friendlys and/or investors) to start using the protocol. However, there’s potentially a compelling argument to be made to build a prototype reference client that mimics the ideal end state by adding functionality to existing RSS feeds (the iMessage approach).</p>
<h3 id="client">Client</h3>
<ul>
<li>RSS reader
<ul>
<li>Having our own client will allow us to dog food the potential “+” features for RSS+</li>
<li>Would also allow us to build the protocol iteratively and not as a protocol initially, i.e. the features are only available within the client</li>
<li>If we think we have some amount of product-market fit, we can submit pull requests to open source feed reader projects</li>
<li>Examples
<ul>
<li>Web: <a href="https://www.google.com/url?q=https://www.newsblur.com/&sa=D&source=editors&ust=1662599945714662&usg=AOvVaw0XJal9Pk56xUGHpnlAM_Uy">NewsBlur</a> (<a href="https://www.google.com/url?q=https://github.com/samuelclay/NewsBlur&sa=D&source=editors&ust=1662599945714793&usg=AOvVaw2rN_BiupKQbApB5kHE8A7T">GitHub</a>)</li>
<li>Mac/iOS: <a href="https://www.google.com/url?q=https://ranchero.com/netnewswire/&sa=D&source=editors&ust=1662599945715084&usg=AOvVaw1jTEYOiXAB9YHYlDOJxTP0">NetNewsWire</a> is <a href="https://www.google.com/url?q=https://github.com/Ranchero-Software/NetNewsWire&sa=D&source=editors&ust=1662599945715342&usg=AOvVaw1R80n3nIgtMO8dLYuNMMQr">open source</a></li>
<li>Desktop: <a href="https://www.google.com/url?q=https://miniflux.app/&sa=D&source=editors&ust=1662599945715845&usg=AOvVaw1YdUSUQkPhKSZyx5aZgHjG">Miniflux</a> (<a href="https://www.google.com/url?q=https://github.com/miniflux&sa=D&source=editors&ust=1662599945716002&usg=AOvVaw2B09ueOHigVl3X33mEVAPr">GitHub</a>)</li>
<li>Web: <a href="https://www.google.com/url?q=https://github.com/swanson/stringer&sa=D&source=editors&ust=1662599945716315&usg=AOvVaw2hqKtuKl058RxGO4XSwZpa">Stringer</a></li>
</ul>
</li>
</ul>
</li>
<li>Chrome extension
<ul>
<li>Fork MetaMask or build a simple prototype Ethereum wallet in a Chrome extension</li>
<li>Add basic functionality related to:
<ul>
<li>Identifying an Ethereum identity associated with a given URL or domain</li>
<li>Primitive social features such as like or retweet</li>
</ul>
</li>
</ul>
</li>
<li>Directory / App Store for RSS feeds
<ul>
<li>Create a directory of interesting blogs and make easy to 1-click subscribe in your current reader</li>
<li>Definitely an example of <a href="https://www.google.com/url?q=http://paulgraham.com/ds.html&sa=D&source=editors&ust=1662599945716923&usg=AOvVaw0zIJ7jgUJk3fwlFbkdyqsx">do things that don’t scale</a>
<ul>
<li>Manually curated to start (which improves quality / taste and limits gaming / spam)</li>
<li>Ask friends and infovores for their OPMLs</li>
<li>Extrapolate based on who popular Twitter accounts follow (URL in bio) or <a href="https://www.google.com/url?q=https://developers.nuzzel.com/&sa=D&source=editors&ust=1662599945717328&usg=AOvVaw3ifllryMJvNACvU05_uZzQ">Nuzzel</a>-style analysis of domains/URLs shared</li>
<li>Leverage Feedly’s directory</li>
</ul>
</li>
</ul>
</li>
</ul>
<h3 id="protocol">Protocol</h3>
<ul>
<li>Work on a spec documentation for RSS+</li>
<li>Release as a GitHub repo as an alpha</li>
<li>Leverage our combined network to <a href="https://www.google.com/url?q=http://paulgraham.com/ds.html&sa=D&source=editors&ust=1662599945717841&usg=AOvVaw3TZsmHzcW6-SJ_NovKFh_D">Collison install</a> the basic implementation of Ethereum identity layer on existing websites</li>
<li>Launch 1-2 experiments publicly that shows what you can do with this new graph
<ul>
<li>At this point maybe you switch over to the highest potential client angle</li>
</ul>
</li>
</ul>
<h2 id="potential-experiments">Potential experiments</h2>
<h3 id="ethtweet">ethtweet</h3>
<p><em>Post a “tweet” to the Ethereum and read other tweets like it</em></p>
<p>Web app that allows you to type in some amount of text in a text box, pay the gas costs, and send a “ethtweet” in a transaction data field. There’s a second tab (“Global”) that shows all previous “ethtweets”.</p>
<h3 id="ethmeme">ethmeme</h3>
<p><em>A Techmeme-like homepage for blogs that embed an Ethereum address</em></p>
<p>Website that shows you an index all blogs that have an .ens address in the <meta /> tag of their .index.html. You can submit the blog to the directory and once indexed it displays all RSS posts in chronological order. (If spamming starts, and you wanted to keep iterating, require each new post to have an associated ETH transaction.)</p>
<h3 id="superlike">SuperLike</h3>
<p><em>“Like” a blog post on-chain via an ERC-20</em></p>
<p>Create a faucet for an ERC-20 token called $SUPERLIKE. Blogs embed an ethereum address in each blog post and you can send 1 SuperLike token to the address via MetaMask. Make a single page block explorer showing the most popular SuperLike content all-time and last 24 hours.</p>
<h3 id="encrypted-tweets">Encrypted Tweets</h3>
<p><em>Add a true crypto Twitter on top of crypto Twitter</em></p>
<p>Fork MetaMask and allow people to do encrypted tweets that need to be decrypted by those with the extension installed. Would natively appear at the top of you feed on the <a href="http://twitter.com/">Twitter.com</a> UI.</p>
<h2 id="questions--underdeveloped-thinking">Questions / underdeveloped thinking</h2>
<p><strong>Do you fork Mastodon to be a reference client / server?</strong></p>
<ul>
<li>Or maybe better model is fork Jekyll static site generator, bundle inside electron app (so you don’t have to install all the libraries via CLI) and have easy posting of content to Github Pages, Netlify, IPFS, etc. (cf. Apple Mail add an account screen)</li>
</ul>
<p><strong>How full stack do you need to be Day 1?</strong></p>
<ul>
<li>iPhone didn’t have 3rd party apps to start and every app was built by Apple</li>
</ul>
<p><strong>Do you do on Ethereum despite congestion today?</strong></p>
<ul>
<li>Or do you use some Layer 2?</li>
<li>Or do you fork a public blockchain that’s better suited to this use case (strip down functionality)
<ul>
<li>The essence of the blockchain here is the ability for any developer to hack on the Twitter graph in a permissionless way – clients, algos, block lists, etc.</li>
</ul>
</li>
<li>Is there a hybrid where you run a separate blockchain that’s partially centralized to start – permissioned nodes / validators – with namespace ownership living on Ethereum to give people comfort that they own their names / leverage DeFi stack?</li>
</ul>
<p><strong>Focus on crypto twitter as initial users?</strong></p>
<ul>
<li>Open to trying new things</li>
<li>Proof of HODL for people you follow?</li>
<li>Ideological appeal?</li>
<li>X Y Z features that improve crypto Twitter UX?</li>
</ul>
<h2 id="related-product-concepts">Related product concepts</h2>
<ul>
<li>Apple’s iMessages (blue bubbles) <a href="https://www.google.com/url?q=https://support.apple.com/en-us/HT207006&sa=D&source=editors&ust=1662599945720038&usg=AOvVaw1bIB2ZGoX4M-lpwP58JrSZ">degrades gracefully into SMS</a> when messaging Android phones or groups with mixed iOS. RSS+ degrades gracefully into RSS?</li>
<li><a href="https://www.google.com/url?q=https://wordpress.com/support/comments/pingbacks/&sa=D&source=editors&ust=1662599945720352&usg=AOvVaw2w2f09-FadbLrChgxpEbyG">Wordpress “pingbacks</a>” — a special type of comment when linking to another blog post. What does this look like on a blockchain?</li>
<li><a href="https://www.google.com/url?q=https://searchengineland.com/rip-technorati-blog-search-rankings-popular-blog-tools-sunset-195186&sa=D&source=editors&ust=1662599945720629&usg=AOvVaw0vJYoAQjeMjKWP6WSv_sg5">Technorati</a> — blog specific search and rankings
<ul>
<li><a href="https://www.google.com/url?q=https://www.techmeme.com/lb&sa=D&source=editors&ust=1662599945720900&usg=AOvVaw0mwpwwgxf3ZLQ5C13B3JHk">Techmeme leaderboards today</a></li>
<li>Do you build the reference Coinmarketcap / Etherscan for this protocol?</li>
</ul>
</li>
<li><a href="https://www.google.com/url?q=https://techcrunch.com/2005/06/14/feedburner-profile/&sa=D&source=editors&ust=1662599945721248&usg=AOvVaw1A8DFknGwfw2j4TdvCOAlC">Feedburner</a> — better analytics for RSS feeds + in-feed ad monetization. Could you use public / private key associated with an account on this network to create individual feeds for premium subscribers?</li>
<li><a href="https://www.google.com/url?q=https://memberful.com/&sa=D&source=editors&ust=1662599945721476&usg=AOvVaw00d45pNTBl6ffKqTHqsQ5y">Memberful</a> — Substack membership stack as a service for Wordpress sites. <a href="https://www.google.com/url?q=https://memberful.com/help/integrate/services/wordpress/private-rss-feeds/%23private-rss-feeds&sa=D&source=editors&ust=1662599945721673&usg=AOvVaw3pwPFiCZE5PvSyM4_krtjY">Private RSS feeds</a> a la Stratechery</li>
<li>Tumblr CMS UI (Twitter is similar at this point – well beyond just text)</li>
<li><a href="https://www.google.com/url?q=https://blog.userfeeds.io/&sa=D&source=editors&ust=1662599945721981&usg=AOvVaw0q-6_3XXa3yksEStWrmfGI">Userfeeds.io</a></li>
<li><a href="https://lbry.com/">https://lbry.com/</a></li>
<li>Pseudonyms
<ul>
<li><a href="https://www.google.com/url?q=https://www.wsj.com/articles/SB10001424052702304743704577380383026226256&sa=D&source=editors&ust=1662599945722423&usg=AOvVaw0bB7q-8ZhtDl44jhhZ3laY">Federalist papers</a></li>
<li>Anonymous social networks have all failed (so far): Secret, YikYak, Blind, JuicyCampus</li>
</ul>
</li>
</ul>
Thu, 08 Sep 2022 14:00:00 +0000Thu, 08 Sep 2022 14:00:00 +0000https://danromero.org/rss-plus.htmlDan RomeroThe original brainstorm for what became FarcasterCryptonative domain registrar<ul>
<li>Build a basic domain registrar for DNS domain names</li>
<li>Each domain name registered is issued an ERC-721 NFT; if the domain name is transferred to a different registrar, the NFT is revoked.</li>
<li>The NFT is composable with all NFT infra — OpenSea, Zora, PartyBid, Fractional, etc.</li>
<li>If you buy and/or control the NFT, you can authenticate your wallet with the registrar to change the name servers, DNS records, etc.</li>
<li>Selling a valuable domain no longer requires dealing with outdated domain brokers, escrow websites like <a href="https://www.afternic.com/">Afternic</a>, no waiting for wires to clear, etc.</li>
<li>Registrar makes money from domain name registrations and maybe partners with 3rd parties for 1-click hosting, email setup, etc.</li>
</ul>
Mon, 20 Jun 2022 14:00:00 +0000Mon, 20 Jun 2022 14:00:00 +0000https://danromero.org/crypto-native-domain-registrar.htmlDan RomeroWhat if every domain name was represented as an NFTWhat I'm excited for this build cycle<p>Below are some loosely-held beliefs I have about what will happen during this crypto winter / build cycle.</p>
<ul>
<li><a href="https://ethereum.org/en/upgrades/merge/">The Merge</a> is successful and energy use meme goes away.</li>
<li>One of the Ethereum L2s breaks away from the pack, de-risking tech choice for builders.</li>
<li>More practical implementations of zero-knowledge proofs (e.g. <a href="https://zkga.me/">Dark Forest</a>) enabling consumer use cases, e.g. trustless anonymous polls or token-enabled experiences.</li>
<li>A 0-to-1 new game that’s fun first and uses a novel, on-chain mechanic second. (Again, similar to Dark Forest, but with a more consumer-friendly experience.) I’m bearish on existing games adding crypto.</li>
<li>A vertically-integrated DAO mobile wallet (think the <a href="https://www.nounsapp.wtf/">Nouns app</a>) with UI-tailored for governance, social, messaging, custody, etc.</li>
<li>A winning <a href="https://eips.ethereum.org/erc">ERC</a> for soulbound NFTs, de-risking tech choice for builders and increasing composability.</li>
<li>Emergence of a credible, centralized startup that issues and maintains on-chain and off-chain credentials that dramatically pulls forward adoption by a few years.</li>
<li><a href="https://www.varunsrinivasan.com/2022/01/11/sufficient-decentralization-for-social-networks">Sufficiently decentralized social networks</a> like <a href="https://farcaster.xyz">Farcaster</a></li>
</ul>
<p>If you’re working on any of the above, send a me a demo via <a href="https://twitter.com/dwr">DM</a>. You can also DM me with your Ethereum address if you want an invite to Farcaster.</p>
Mon, 20 Jun 2022 14:00:00 +0000Mon, 20 Jun 2022 14:00:00 +0000https://danromero.org/excited-for-this-build-cycle.htmlDan RomeroThe Merge, L2s, practical ZKPs and moreconfig.xyz<ul>
<li>Call the service config</li>
<li>Mint an NFT that maps to an off-chain URL</li>
<li>URL is flat file JSON and contains key-value pairs of common settings, e.g. display name, avatar, language, font size, whether you want dark mode turned on, links to other social networks</li>
<li>For more sensitive information — email address, granular notification preferences, block list, mute list, should algorithms be turned on or off — all exist as pointers to encrypted off-chain datastore like <a href="https://www.privy.io/">privy.io</a>.</li>
<li>When a user uses “Connect Wallet” for an app / website, their config is automatically imported and any sensitive data can be requested by the app and approved by the user in a single click.</li>
<li>In theory this can be done with ENS but expensive to initially set and update, JSON format would be extensible and lower the friction for permissionless innovation</li>
</ul>
Mon, 07 Mar 2022 14:00:00 +0000Mon, 07 Mar 2022 14:00:00 +0000https://danromero.org/config-xyz.htmlDan RomeroPortable user settings as an NFT.Podcasting distribution is the problem to solve<p>If Joe Rogan were to leave centralized web2 platforms like Spotify, YouTube, Apple Podcasts, where his content is <em>hosted</em> is a way less interesting issue than how his content is <em>distributed</em>.</p>
<p>Prior to going exclusive with Spotify, Rogan used the decentralized protocol that most other podcasters use, RSS. All of the centralized podcast platforms were able to list the podcast by simply subscribing to his RSS feed.</p>
<p>However, the podcaster <> listener relationship is not direct; the podcast clients/platforms listeners choose as their default podcast player have the ability to block access or hide content from given feed. But since there are many competing clients, listeners can easily switch to a client that gives them the freedom to subscribe to whatever podcast RSS they want. However, not being on popular platforms like Apple, Spotify and YouTube will significantly reduce total audience size.</p>
<p>A potential improvement for podcasters on the existing decentralized RSS podcast implementation would be a standard for clients to allow users to opt-in to an email list (or other direct messaging) when they subscribe to the show.</p>
<p>OPML export does exist in some apps like <a href="https://gist.github.com/jamesstout/a4050fdfda4f1fad5d5637ff35293549">Overcast</a> and <a href="https://support.pocketcasts.com/article/im-new-to-pocket-casts-how-do-i-import-my-opml-2/">Pocket Casts</a>, but too technical for most people. The beauty of podcasts and RSS today is the technical complexity has been abstracted. Sadly, unlikely that centralized platforms will want to make OPML export easy.</p>
<p><em>This first appeared on <a href="https://twitter.com/dwr/status/1490038619288977408">Twitter</a>.</em></p>
Sat, 05 Feb 2022 19:09:00 +0000Sat, 05 Feb 2022 19:09:00 +0000https://danromero.org/podcast-distribution-problem.htmlDan RomeroBuilding a direct connection between podcasters and listeners is unsolved.Crypto things I'm excited about<p>Crypto things that aren’t here yet (or even built) but I’m excited for:</p>
<ul>
<li><a href="https://twitter.com/dwr/status/1403389706105098241">NTNFTs</a> (<a href="https://vitalik.ca/general/2022/01/26/soulbound.html">soulbound NFTs</a>)</li>
<li>zero-knowledge proof of asset / credential ownership</li>
<li>zero-knowledge secret ballot voting</li>
<li>new apps / services that allow you to bring your own recommendation algorithm</li>
</ul>
Fri, 04 Feb 2022 17:00:00 +0000Fri, 04 Feb 2022 17:00:00 +0000https://danromero.org/excited-about-crypto-feb-22.htmlDan RomeroWe're still in the first innning of new crypto primitives.Free startup ideas<p>Below is a list of startup ideas that might be interesting to work on.</p>
<p><strong>Strava for cooking</strong><br />
Start by building the HUD for home cooks and then tack on a social network. More <a href="https://danromero.org/strava-for-cooking.html">here</a>.</p>
<p><strong>Delete Me (from the Internet)</strong><br />
Create an automated private investigator using common Google queries and default public but likely forgotten about social media services. Charge $99 to clean up old services, removal from databases, etc. (similar to DoNotPay). Add a subscription service for ongoing security monitoring (e.g. haveibeenpwned.com).</p>
<p><strong>Goodreads + GitHub</strong><br />
Build single-player tool for serious learners: personal library with emphasis on SRS retention (automagically create Anki decks from Kindle highlights). Ability to fork and clone personal book repos. Open API from Day 1. Focus on desktop, not mobile. Eventually add a social network.</p>
<p><strong>Streaming Buddy</strong><br />
Re-create the feel of watching live TV + Twitter for async streamed shows. Recommendations across various services (editorial + user-generated content) serves as a top-of-funnel modern ‘TV Guide’.</p>
<p><strong>Instagram for enterprise</strong><br />
Feed with interesting, relevant visual posts (data, slides, links, etc.); designed to be passive (i.e. OK to miss posts). This stuff gets easily lost in Slack today.</p>
<p><strong>Meeting Guru</strong><br />
Integrate with various document, calendar and video conferencing services (i.e. a thin client). Survey participants after the meeting about effectiveness. Analytics for executive team about meeting effectiveness, efficiency, etc.</p>
<p><strong>Clubhouse for enterprise</strong><br />
Uberconference but without the concept of “calls”. Make it work really well when on a lower bandwidth cellular connection (i.e. dialing in from an Uber).</p>
<p><strong>Honey for Wirecutter</strong><br />
Surface even better recommendations for a given SKU via Chrome extension. Use user-generated data to bootstrap your own product review site. Monetize via referrals.</p>
<p><strong>Wirecutter + fiverr</strong><br />
Pay a small-ish amount of money for one-off, more tailored product research. (This already exists on many subreddits for free.)</p>
<p><strong>Spotify + Cameo</strong><br />
Hire a remote DJ for a party, evening, etc. (Spotify has an API). Start with amateurs, work your way up to Kygo.</p>
<p><strong>Replace investors@ Google Groups</strong><br />
Make messages free and encrypted to gain trust. Take over the flow for Docusign investor docs and/or the USD wire workflow over time. Probably a feature for Carta or Pulley but may be a sufficiently different space (messaging vs. cap table management).</p>
<p><em>If you are working on any of these, feel free to send me an email at hello@danromero.org. Fair warning: I will likely pass without a meeting unless you have a compelling demo or spectacular pitch deck.</em></p>
Thu, 18 Mar 2021 17:00:00 +0000Thu, 18 Mar 2021 17:00:00 +0000https://danromero.org/free-startup-ideas.htmlDan Romero11 ideas. No guarantees they are good, though.2020 booklist<p>Below is a list of books I read this year. The first ten books were my favorites (in no particular order).</p>
<p>As for themes: continued the theme from the last few years on “how the world became modern” (loosely defined); a deep-dive into Communism; American political evolution post-1960s; Middle East geopolitics; Ancient Rome; and the history of Christianity.</p>
<p>The books had an older average publication date than in years past. I didn’t read a single “business” book.</p>
<p>My primary source for book recommendations was <a href="https://marginalrevolution.com/marginalrevolution/category/books">Marginal Revolution</a>. After that, I tended to dig through the bibliographies of books I was especially enjoying (e.g. Before European Hegemony and Civilization and Capitalism were nice discoveries).</p>
<p>For next year, I’m likely to continue with this year’s themes, as well as exploring the French Revolution, Islam, and the history of California.</p>
<p>Finally, here’s <a href="https://danromero.org/2019-booklist.html">last year’s booklist</a>.</p>
<ol>
<li><a href="https://amzn.to/2X1rwB3">God and Gold: Britain, America, and the Making of the Modern World</a></li>
<li><a href="https://amzn.to/3n4VRt2">History’s Locomotives: Revolutions and the Making of the Modern World</a></li>
<li><a href="https://amzn.to/3pBW8Fv">Speeding the Net: The Inside Story of Netscape and How It Challenged Microsoft</a></li>
<li><a href="https://amzn.to/382dm9e">The WEIRDest People in the World: How the West Became Psychologically Peculiar and Particularly Prosperous</a></li>
<li><a href="https://amzn.to/380TvqU">Before European Hegemony: The World System A.D. 1250-1350</a></li>
<li><a href="https://amzn.to/3953Txp">The Hot Hand</a></li>
<li><a href="https://amzn.to/3n6H3Ku">Reaganland: America’s Right Turn 1976-1980</a></li>
<li><a href="https://amzn.to/2L72uxZ">The Second Amendment: A Biography</a></li>
<li><a href="https://amzn.to/382YK9v">The Coddling of the American Mind: How Good Intentions and Bad Ideas Are Setting Up a Generation for Failure</a></li>
<li><a href="https://amzn.to/3519N15">The English and Their History</a></li>
<li><a href="https://amzn.to/2X2nbgU">Lenin: The Man, the Dictator, and the Master of Terror</a></li>
<li><a href="https://amzn.to/3o5muiS">The Darkening Age: The Christian Destruction of the Classical World</a></li>
<li><a href="https://amzn.to/3hv0nQB">Rubicon: The Last Years of the Roman Republic</a></li>
<li><a href="https://amzn.to/2LcnfrL">Absolute Monarchs: A History of the Papacy</a></li>
<li><a href="https://amzn.to/3huQPFh">Soviet Tragedy: A History of Socialism in Russia</a></li>
<li><a href="https://amzn.to/34ZRzNA">Alaric the Goth: An Outsider’s History of the Fall of Rome</a></li>
<li><a href="https://amzn.to/2WXKY1R">A Culture of Growth: The Origins of the Modern Economy</a></li>
<li><a href="https://amzn.to/2WYAoHL">The Rise and Decline of Nations: Economic Growth, Stagflation, and Social Rigidities: Economic Growth, Stagflation and Social Rigidities</a></li>
<li><a href="https://amzn.to/3aTEgSF">The Russian Revolution: A New History</a></li>
<li><a href="https://amzn.to/2LdRIFV">The Kill Chain: Defending America in the Future of High-Tech Warfare</a></li>
<li><a href="https://amzn.to/38TpzvY">MBS: The Rise to Power of Mohammed bin Salman</a></li>
<li><a href="https://amzn.to/3848RLk">Disunited Nations: The Scramble for Power in an Ungoverned World</a></li>
<li><a href="https://amzn.to/2KO3Iy4">Saudi Inc.</a></li>
<li><a href="https://amzn.to/3aXhSb5">The Black Book of Communism (assorted sections)</a></li>
<li><a href="https://amzn.to/2KPhYGZ">Civilization and Capitalism 15th-18th Century (assorted sections across 3 volumes)</a></li>
<li><a href="https://amzn.to/3babsFJ">Empire of Cotton: A Global History</a></li>
<li><a href="https://amzn.to/3huNR3D">An Open Letter to Open-Minded Progressives</a></li>
<li><a href="https://amzn.to/3hwIGjr">Bronze Age Mindset</a></li>
<li><a href="https://amzn.to/2JyDK0Z">Foundation (re-read)</a></li>
<li><a href="https://amzn.to/2JyDK0Z">Foundation and Empire (re-read)</a></li>
<li><a href="https://amzn.to/2JyDK0Z">Second Foundation (re-read)</a></li>
<li><a href="https://amzn.to/3rHVuZ8">Elon Musk: Tesla, SpaceX, and the Quest for a Fantastic Future (re-read)</a></li>
<li><a href="https://amzn.to/3rGNF5Z">City of Quartz: Excavating the Future in Los Angeles</a></li>
</ol>
Thu, 31 Dec 2020 17:00:00 +0000Thu, 31 Dec 2020 17:00:00 +0000https://danromero.org/2020-booklist.htmlDan RomeroBooks I read in 2020.Strava for cooking<p><a href="https://www.strava.com/">Strava</a> is a social network for serious-yet-amateur athletes. It’s also a vertical social network with some powerful <a href="https://twitter.com/dwr/status/1273307320911450112">characteristics</a>:</p>
<ul>
<li>Single-player tool with multiplayer social feed</li>
<li>The more you use the app, the more likely you are to do the atomic behavior.</li>
<li>Doing more of the atomic behavior is actually good for you.</li>
</ul>
<p>I believe there’s an opportunity for a vertical social network built for serious-yet-amateur home cooks. Initial target users would be fans of influencers like <a href="https://www.youtube.com/channel/UCqqJQ_cXSat0KIAVfIfKkVA">J. Kenji López-Alt</a>, <a href="https://www.bingingwithbabish.com/">Binging with Babish</a> and <a href="https://www.youtube.com/channel/UCPzFLpOblZEaIx2lpym1l1A">Alex French Guy Cooking</a>. (All of their audiences have <a href="https://socialblade.com/youtube/user/kenjialt/monthly">significantly increased</a> during <a href="https://twitter.com/dwr/status/1274139593831362561">COVID</a>.)</p>
<p>Similar to Strava, you’d start by offering <a href="https://cdixon.org/2010/06/12/designing-products-for-single-and-multiplayer-modes">single-player tools</a>. For Strava that’s been <a href="https://blog.strava.com/routes/">route planning</a> and <a href="https://support.strava.com/hc/en-us/articles/216917137-What-s-a-segment-">segments</a>; for cooking that might be a database of web-crawled recipes with a <a href="https://twitter.com/kevin/status/1256610048194695170">Gantt chart interface</a> to manage the timing of a multi-course meal. As a user base develops, you’d start adding in <a href="https://cdixon.org/2015/01/31/come-for-the-tool-stay-for-the-network">multiplayer social features</a>.</p>
<p>There are plenty of ways you could monetize. Affiliate links are one avenue (cookbooks, kitchen equipment). Paid subscriptions (pro features in app, weekly recipes from celebrity chefs) is another.</p>
<p>At-scale, Strava for cooking would become the go-to place for <a href="https://www.pinterest.com/">cooking inspiration</a>, <a href="https://cooking.nytimes.com/">recipes</a>, <a href="https://www.youtube.com/">videos</a>, <a href="https://www.nytimes.com/wirecutter/kitchen-dining/">kitchen equipment</a>, and <a href="https://www.instagram.com/">internet socializing</a> about food.</p>
<p><em>This idea <a href="https://rfs100.substack.com/p/social-avatars-trustpilot-for-1099">originally appeared</a> in <a href="https://rfs100.com/">RFS 100</a>. There’s some additional feedback on the Strava for X concept <a href="https://julian.digital/2020/08/06/proof-of-x/">here</a>.</em></p>
Sat, 21 Nov 2020 15:00:00 +0000Sat, 21 Nov 2020 15:00:00 +0000https://danromero.org/strava-for-cooking.htmlDan RomeroSocial network for serious amateur cooksThe toothbrush test<p>A helpful heuristic I use to evaluate consumer apps is the toothbrush test. I first learned about it in 2014 in a <a href="https://dealbook.nytimes.com/2014/08/17/in-silicon-valley-mergers-must-meet-the-toothbrush-test/">NY Times article</a>:</p>
<blockquote>
<p>When deciding whether Google should spend millions or even billions of dollars in acquiring a new company, its chief executive, Larry Page, asks whether the acquisition passes the toothbrush test: Is it something you will use once or twice a day, and does it make your life better?</p>
</blockquote>
<blockquote>
<p>The esoteric criterion shuns traditional measures of valuing a company like earnings, discounted cash flow or even sales. Instead, Mr. Page is looking for usefulness above profitability, and long-term potential over near-term financial gain.</p>
</blockquote>
<blockquote>
<p>Google’s toothbrush test highlights the increasing autonomy of Silicon Valley’s biggest corporate acquirers — and the marginalized role that investment banks are playing in the latest boom in technology deals.</p>
</blockquote>
<p>Surprisingly, the toothbrush test is not very popular in 2020 Silicon Valley jargon. It might be that Larry Page doesn’t have a social media presence (cf. Elon Musk). Another reason may be there are fewer people working on new consumer apps vis-à-vis enterprise SaaS.</p>
<p>But if you think of most successful consumer apps they satisfy the test: search, email, messaging, social media, streaming media. Toothbrush test products usually are free, ad-supported services or subscriptions. One exception to this are ridesharing and delivery apps like Uber and DoorDash—they are usually used a few times a week and charge a fee.</p>
<p>Of course, there are successful consumer apps that don’t satisfy the toothbrush test: many marketplaces (e.g. Airbnb) have semi-monthly or semi-yearly cadence. To make up for the lower frequency of use, these marketplaces tend to charge a relatively large fee. For example, <a href="https://www.airbnb.com/help/article/1857/what-are-airbnb-service-fees">Airbnb charges consumers approximately 14%</a> (in addition to a 3% fee for hosts).</p>
<p>Entrepreneurs and investors should determine whether a new consumer app has the potential to be used 1-2 times per day. If not, then will they be able to charge a premium fee to make up for the lack of frequent use?</p>
Tue, 20 Oct 2020 18:00:00 +0000Tue, 20 Oct 2020 18:00:00 +0000https://danromero.org/the-toothbrush-test.htmlDan RomeroA helpful heuristic I use to evaluate consumer apps is the toothbrush test.Significantly worse or non-existent<p>One important question when evaluating a new product or technology is “will people or companies adopt this?”. I’ve found the best way to answer this is with another question: “Is the next best alternative <em>significantly worse or non-existent</em>?”. If yes, then the product or technology has a good chance of adoption; if no, it’s likely to remain unadopted. This heuristic is particularly useful for navigating the <a href="https://cdixon.org/2013/08/04/the-idea-maze">startup idea maze</a>.</p>
<p>In Clayton Christensen’s <a href="https://hbr.org/2016/09/know-your-customers-jobs-to-be-done">jobs to be done framework</a>, people and companies <em>hire</em> products and technologies to solve problems, i.e. <em>jobs</em>. People hire Google to search for something or Amazon to buy something. But people were searching and buying before Google or Amazon—so why did each get adopted?</p>
<p>In each case, the next best alternative was significantly worse or non-existent: pre-Google search options were slower and less relevant (significantly worse), and in many cases the information had yet to be indexed (non-existent); pre-Amazon, buying a basket of items required visiting multiple stores and were likely more expensive (significantly worse), and niche items were not available from local stores (non-existent).</p>
<p><em>Significantly</em> worse—as opposed to just worse—is a subjective and in some cases tricky distinction. Few people will switch from a marginally worse alternative. Whether it’s laziness, ignorance or the power of habit, an existing worse alternative will have a status quo bias that can be hard to overcome. Significantly worse alternatives, however, are usually associated with enough pain and dissatisfaction that people are happy to switch.</p>
<p>So how can you determine whether the next best alternative is <em>significantly</em> worse? Peter Thiel’s <a href="https://blakemasters.com/post/23250566538/peter-thiels-cs183-startup-class-12-notes">10x better framework</a> is useful: if a new product or technology is 10x better, it’s likely that the next best alternative is significantly worse; something that’s only 10% better is unlikely to be able to overcome the inertia of the existing choice and/or behavior. Another sign of significantly worse is, when asking someone about the product, they lead with a complaint, e.g. “it’s expensive” or “it’s slow”.</p>
<h2 id="cryptocurrency-examples">Cryptocurrency examples</h2>
<p>Significantly worse or non-existent has been an effective way to evaluate what ideas will work in cryptocurrency. Bitcoin and public blockchains are true technology breakthroughs: until invented, the ability to transfer value in a trustless, decentralized, digital manner was non-existent. But just because something exists doesn’t mean it will be adopted.</p>
<p>For example, in the early 2010s, many thought Bitcoin would be widely adopted by e-commerce websites given Bitcoin was lower cost, global, instantly settled and lacked chargeback risk. But while Bitcoin satisfied significantly worse or non-existent from the e-commerce website perspective, it did not answer that question for consumers: they already had credit/debit cards, nearly every e-commerce website accepted cards, and rewards points and chargebacks were popular consumer features of cards. Further, Bitcoin was relatively hard to acquire and required gain/loss tax accounting for every transaction. Not surprisingly, Bitcoin payments were not very popular for mainstream e-commerce websites. (However, for e-commerce websites where payment service providers were non-existent, e.g. Silk Road (dark/grey market goods) and SatoshiDice (online gambling), Bitcoin was adopted.)</p>
<p>A similar story exists in <a href="https://blog.coinbase.com/a-beginners-guide-to-decentralized-finance-defi-574c68ff43c4">DeFi</a>. Traditionally, cryptocurrencies have traded on centralized exchanges, offering users liquidity, functionality and usability that was non-existent on blockchains, i.e. you could not trade Bitcoin for US dollars on-chain. However, centralized exchanges had some disadvantages: they were susceptible to hacks, subject to regulatory restrictions, and developers of new crypto tokens found it hard/slow to get their tokens listed. As Ethereum became more popular, 0x developed a decentralized exchange protocol addressing the disadvantages of centralized exchanges. But usage was only marginal: 0x suffered from low liquidity. A few years later, Uniswap solved the liquidity problem (via an automated market maker which natively incentivized liquidity providers), and <a href="https://www.theblockcrypto.com/linked/79775/uniswap-coinbase-monthly-volume-september">trading volumes quickly grew</a> to rival centralized exchanges.</p>
<p>The Bitcoin e-commerce and decentralized exchange examples illustrate an important point about significantly worse or non-existent: it’s not sufficient to solve problems if you create a new, more fundamental problem. For Bitcoin e-commerce, while Bitcoin solved problems for merchants, it created new problems for consumers. And in the case of early decentralized exchange protocols, despite solving the security and listing scarcity problems, the lack of liquidity was a more pressing problem that centralized exchanges had already solved.</p>
<p>In conclusion, entrepreneurs and investors should spend time understanding what problem a new product or technology is solving, are the alternatives significantly worse or non-existent, and does the new thing surface new problems that the worse alternative has already solved.</p>
Mon, 05 Oct 2020 17:00:00 +0000Mon, 05 Oct 2020 17:00:00 +0000https://danromero.org/significantly-worse-or-non-existent.htmlDan RomeroOne important question when evaluating a new product or technology is “will people or companies adopt this?”.Good and bad reasons to do an MBA<p>I occasionally get introduced to people considering an MBA who have long-term aspirations to work in tech. It’s typically someone who has spent a few years after graduating from college working in management consulting or investment banking; others have finished consulting/banking and have an additional few years experience working at an established tech company or lower growth/later stage startup.</p>
<p>My general advice is an MBA is expensive both in direct tuition costs and, more importantly, indirect opportunity costs. While direct tuition costs are straightforward to value, most people tend to underestimate an MBA’s true opportunity cost, especially if one chooses a post-MBA job primarily based on cash compensation to help pay off student loans. The 2 to 4 years of <em>not</em> working in your long-term field has significant costs when you consider that work experience is a non-linear function, i.e. there are compounding benefits to continuous work experience.</p>
<p>Further, the average person gets more risk-adverse as they age–so the risky-but-high-upside opportunity that would have been attractive as a single 20-something is less attractive as someone in their 30s with a young family.</p>
<p>That said, I do think there are good and bad reasons for doing an MBA–but I do not think it’s usually an ROI positive investment for people who want to work in tech.</p>
<h2 id="good-reasons">Good reasons</h2>
<p><strong>Fun:</strong> you are looking for a 2-year break from 80-hour work weeks and are keen to socialize with like-minded (mostly) single peers and getting to travel. This is expensive (see the opportunity cost paragraph above), but for some the utility is worth it. Of course, having fun doesn’t improve your qualification for a job in tech.</p>
<p><strong>Career shift:</strong> you started your career in something non-business oriented–teaching, in the military, working at an NGO–and are looking to break into business. Related, you started your business career in a more narrow field–pharmaceutical sales, automotive engineering, etc.–and want to get more general exposure to business and/or switch industries. As for working in tech, the MBA itself doesn’t add much in the way of relevant skills for a tech startup. You’d be better off taking an entry-level customer support or ops job at a startup and making the shift internally to another function after you’ve proven yourself.</p>
<p><strong>“Requirement”</strong>: you are interested in working at more established Fortune 500 companies or certain types of consulting or investment firms that “require” an MBA for a specific role. I’m the most skeptical of this reason when I hear it–I can usually quickly find a counter-example via Google or LinkedIn. But for someone who wants to do career shift into management consulting, an MBA from a top-tier business school allows of a chance at interviewing. I’m not aware of any quality technology company (later stage or startup) that requires an MBA.</p>
<h2 id="bad-reasons">Bad reasons</h2>
<p><strong>“Learning business”:</strong> the best way to learn about business is to do actual business. This is even more true about entrepreneurship: you learn entrepreneurship by being an entrepreneur. Further, the vast majority of business school case studies are available via [blog posts], books or even [a la carte] from the business schools themselves.</p>
<p><strong>“The Network”:</strong> again, the best way to build a relevant professional network is to work in the relevant industry. You’ll be interacting with people both internally and externally from your company in an actual work setting vs. academic setting. Additionally, the varying levels of tenure and seniority will offer you more opportunities for future jobs and future talent to recruit. Contrast this to business school: it’s academic, i.e. non-real world, environment and the closest connections you’ll make in business school will almost certainly be your classmates–who are also entering back into the work force at roughly the same seniority/responsibility as you are.</p>
<p><strong>“The Resume”:</strong> there’s a myth that having an MBA will open up a category of jobs not available to normal people. While this may be true in consulting or banking, in most high-growth technology companies and/or startups, an MBA is at best neutral and at worst a negative on a resume. These companies will inevitably favor the person with 2 years of on-the-job learning over 2 years of academic learning.</p>
<p><strong>“X successful person has an MBA”:</strong> correlation not causation. Further, if you are trying to replicate someone else’s career path in order to achieve a similar level of success, it’s unlikely to happen for the simple reason that the successful person’s arbitrage opportunity is no longer available.</p>
<p><em>Caveat lector: I do not have an MBA.</em></p>
Tue, 01 Sep 2020 17:00:00 +0000Tue, 01 Sep 2020 17:00:00 +0000https://danromero.org/mba-reasons.htmlDan RomeroThe pros and (mostly) cons of an MBA for people who want to work in tech.Erik Torenberg's Venture Stories podcast interview<p>I recently went on the <a href="https://www.villageglobal.vc/podcast/">Venture Stories podcast</a> with <a href="https://twitter.com/eriktorenberg">Erik Torenberg</a>. Below are some links to the episode:</p>
<ul>
<li><a href="https://podcasts.apple.com/us/podcast/what-dan-romero-thinks-about-basically-everything/id1316769266?i=1000485193433">Apple Podcasts</a></li>
<li><a href="https://overcast.fm/+LDKc8Lu8Y">Overcast</a></li>
<li><a href="https://open.spotify.com/episode/1LZVgO8rbgp9oXcLUBEuGC">Spotify</a></li>
</ul>
<p>I mentioned a number of books:</p>
<ul>
<li><a href="https://amzn.to/39BRCjP">The Arabs</a></li>
<li><a href="https://amzn.to/3hQp2hc">City of Fortune</a></li>
<li><a href="https://amzn.to/3ggXxNC">Why the West Rules—for Now</a></li>
<li><a href="https://amzn.to/2P8Fuxk">The Accidental Superpower</a></li>
<li><a href="https://amzn.to/36jUFKM">The Prize</a></li>
<li><a href="https://amzn.to/332X4Lf">The Master Switch</a></li>
<li><a href="https://amzn.to/308Mr7Q">Enlightenment Now</a></li>
<li><a href="https://amzn.to/310B7tx">The Kill Chain</a></li>
<li><a href="https://amzn.to/39L5GYb">Why Nations Fail</a></li>
<li><a href="https://amzn.to/2PaXqag">The Black Book of Communism</a></li>
<li><a href="https://amzn.to/3hRFDl8">Nixonland</a></li>
<li><a href="https://amzn.to/2tkaq64">Dominion</a></li>
<li><a href="https://amzn.to/310ZAPy">The Sovereign Individual</a></li>
<li><a href="https://amzn.to/314gA7k">Speeding the Net</a></li>
<li><a href="https://amzn.to/39L5CaT">Saudi Inc.</a></li>
<li><a href="https://amzn.to/39BsEB2">Basic Economics</a></li>
</ul>
<p>As well as some blog posts and papers:</p>
<ul>
<li><a href="https://twitter.com/dwr/status/1285682980766257152">Peter Thiel on his goal of reducing violence</a></li>
<li><a href="https://en.wikipedia.org/wiki/Lindy_effect">Lindy effect</a></li>
<li><a href="https://www.mercatus.org/publications/healthcare/why-are-prices-so-damn-high">Why Are the Prices So Damn High?</a></li>
<li><a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2423461">Bitcoin Financial Regulation: Securities, Derivatives, Prediction Markets, and Gambling</a></li>
<li>LT3000 <a href="https://lt3000.blogspot.com/2020/03/coronapocalypse-some-thoughts.html">March 2020 post</a> and <a href="https://lt3000.blogspot.com/2020/05/coronavirus-update-from-unknown-unknown.html">May 2020 post</a></li>
<li>Balaji Srinivasan’s <a href="https://spark-public.s3.amazonaws.com/startup/lecture_slides/lecture5-market-wireframing-design.pdf">idea maze</a> and Chris Dixon’s <a href="https://cdixon.org/2013/08/04/the-idea-maze">version</a></li>
<li>Marc Andreessen’s <a href="https://pmarchive.com/guide_to_startups_part4.html">The only thing that matters</a> post</li>
</ul>
Wed, 29 Jul 2020 17:00:00 +0000Wed, 29 Jul 2020 17:00:00 +0000https://danromero.org/venture-stories-podcast-interview.htmlDan RomeroI recently went on the Venture Stories podcast with Erik Torenberg.Netscape's contributions<p>A short list of technical contributions from Netscape:</p>
<ul>
<li>First mainstream web browser and the source of the <a href="https://en.wikipedia.org/wiki/Firefox_early_version_history">initial codebase for Firefox</a> — <a href="https://www.oreilly.com/openbook/opensources/book/netrev.html">an oral history of Netscape’s contribution to Mozilla</a>the first viable competitor to Microsoft’s Internet Explorer; Google’s Chrome and Apple’s Safari followed (not based on Netscape source code).</li>
<li><a href="https://en.wikipedia.org/wiki/Transport_Layer_Security">SSL</a> — predecessor to modern TLS, essentially for secure communication and e-commerce (i.e. sending credit card details via unencrypted plaintext doesn’t scale!). Netscape also worked to allow encryption to be widely accessible; as late as 1997 <a href="https://www.nytimes.com/1997/04/07/business/us-restrictions-on-exports-aid-german-software-maker.html">browser encryption was export restricted</a>.</li>
<li><a href="https://en.wikipedia.org/wiki/JavaScript">Javascript</a> — as of April 2020, Javascript is the <a href="https://insights.stackoverflow.com/survey/2019">most popular programming</a> language in the world.</li>
</ul>
Thu, 23 Apr 2020 17:00:00 +0000Thu, 23 Apr 2020 17:00:00 +0000https://danromero.org/netscape-contributions.htmlDan RomeroA short list Netscape's contributions to the modern Internet.COVID-19 learning<p>The following is a running list of concepts I learned from following coverage <a href="https://en.wikipedia.org/wiki/2019%E2%80%9320_coronavirus_pandemic">COVID-19</a>.</p>
<ul>
<li><a href="https://www.youtube.com/watch?v=gxAaO2rsdIs">Simulating an epidemic</a></li>
<li><a href="https://www.meltingasphalt.com/interactive/outbreak/">Kevin Simler’s Outbreak</a></li>
<li><a href="https://www.youtube.com/watch?v=qJlP91xjvsQ">How Moderna’s potential mRNA-1273 vaccine works</a></li>
<li><a href="https://en.wikipedia.org/wiki/Serology">Serology</a></li>
<li><a href="https://en.wikipedia.org/wiki/Antibody-dependent_enhancement">Antibody-dependent enhancement</a></li>
<li><a href="https://en.wikipedia.org/wiki/Cytokine_release_syndrome">Cytokine storm</a></li>
</ul>
Mon, 23 Mar 2020 17:00:00 +0000Mon, 23 Mar 2020 17:00:00 +0000https://danromero.org/covid-19-learning.htmlDan RomeroA running list of concepts I learned from COVID-19.What to watch March 2020<p>Yesterday I <a href="https://twitter.com/dwr/status/1241107873305853953">asked on Twitter</a> for recommendations. Here’s the list.</p>
<table>
<thead>
<tr>
<th>Film / Show</th>
<th>Recommendation from</th>
</tr>
</thead>
<tbody>
<tr>
<td><a href="https://www.hulu.com/series/devs-fd2f6cc3-dafc-4741-ae2e-d86494f3ca51&sa=D&ust=1584803439353000&usg=AFQjCNGVh97_zDVsGfsLPRb1RJVbGsDoFA">Devs</a></td>
<td>@Besvinick, @restudio101, @austinmcraig, @_arbitraged</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80021955?source%3D35&sa=D&ust=1584803439354000&usg=AFQjCNHvsNnnrEKsgbdZ6v_ZHRMEugdbcg">Better Call Saul</a></td>
<td>@kchristidis_, @mrrolfe</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80204890?source%3D35&sa=D&ust=1584803439354000&usg=AFQjCNFusfi96ltRSyVUXbAmfbAGWmNThQ">Drive to Survive</a></td>
<td>@Victor_Patru, @__afischer</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B00KGTU316/ref%3Datv_dl_rdr&sa=D&ust=1584803439354000&usg=AFQjCNFzqtAj2t5wepS2QAZnX8WFwjOS8g">The Sopranos</a></td>
<td>@lehrjulian, @scottmledbetter</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80136321?source%3D35&sa=D&ust=1584803439354000&usg=AFQjCNFmPIXedYxWwJjce3ROi9X-yioErA">Bablyon Berlin</a></td>
<td>@sriramk, @notaprlldgtdwyr</td>
</tr>
<tr>
<td><a href="https://play.hbonow.com/series/urn:hbo:series:GVU2bygQ1go7DwvwIAT3r?camp%3DSearch%26play%3Dtrue&sa=D&ust=1584803439354000&usg=AFQjCNFHiAQCXOBOYkQGX1fXV7GyRqTB1g">Curb Your Enthusiasm</a></td>
<td>@ryandawidjan, @Besvinick</td>
</tr>
<tr>
<td><a href="https://play.hbonow.com/series/urn:hbo:series:GV7xwpQNK8MJfPwEAAAG_?camp%3DSearch%26play%3Dtrue&sa=D&ust=1584803439354000&usg=AFQjCNGO-Q95l-RMJtWKNbxdqIGbiAFdlw">Westworld Season 3</a></td>
<td>@mckaywrigley, @austinmcraig</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B082L5TTCQ/ref%3Datv_dl_rdr&sa=D&ust=1584803439355000&usg=AFQjCNHwIwKNyY_NIge0LJ2xP_Ec4e3QEA">The Expanse</a></td>
<td>@proto_hiro, @austinmcraig</td>
</tr>
<tr>
<td><a href="https://play.hbonow.com/series/urn:hbo:series:GXflGcQEvOZWdkQEAAAE3?camp%3DSearch%26play%3Dtrue&sa=D&ust=1584803439355000&usg=AFQjCNHjKS1JZu1v83C1kZ0KjHKX6-7V6A">McMillions</a></td>
<td>@sriramk</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80161497&sa=D&ust=1584803439355000&usg=AFQjCNHqxpOPvbRU9QI09MVgFeTfkSqZww">Toys That Made Us</a></td>
<td>@sriramk</td>
</tr>
<tr>
<td><a href="https://itunes.apple.com/no/movie/born2drive/id1466251067&sa=D&ust=1584803439355000&usg=AFQjCNEVEB_OOYV4R81loOyTgBr0Dn5Akg">Born to Drive</a></td>
<td>@context_ing</td>
</tr>
<tr>
<td><a href="https://www.hulu.com/series/little-fires-everywhere-bce24897-1a74-48a3-95e8-6cdd530dde4c&sa=D&ust=1584803439355000&usg=AFQjCNF5hKDAgEwBeaBxQ0TUeKpfnpho3g">Little Fires Everywhere</a></td>
<td>@jorilallo</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80113701&sa=D&ust=1584803439355000&usg=AFQjCNEI27wJT2LpBYXWccDYunQ4j1dzHQ">The Good Place</a></td>
<td>@arjunbl</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B07PH2RH91/ref=atv_dl_rdr">Snatch</a></td>
<td>@dredesigns</td>
</tr>
<tr>
<td><a href="https://www.cbs.com/shows/star-trek-picard/video/hB4J7gllhhJUPRpYkgpQwjYb2sTfwIr9/star-trek-picard-the-end-is-the-beginning/?searchReferral%3Dgoogle&sa=D&ust=1584803439355000&usg=AFQjCNFzckAfANFoXKrkFMZvo8e4wsypgA">Picard</a></td>
<td>@ArtirKel</td>
</tr>
<tr>
<td><a href="https://www.hulu.com/series/b8cb8b11-74a6-4169-9ef2-36845e01aef9&sa=D&ust=1584803439356000&usg=AFQjCNFlI-j5LbhaXFYcL5L-IfOfNRMJRw">Black Monday</a></td>
<td>@tomazstolfa</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/81159258?source%3D35&sa=D&ust=1584803439356000&usg=AFQjCNGbXBiWdaqWyH5oAhdxushoMAxaVg">Crash Landing on You</a></td>
<td>@kamal</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/81193309?source%3D35&sa=D&ust=1584803439356000&usg=AFQjCNFPSFC8kT8Wj97UVGb043Y2NqmHMQ">Itaewon Class</a></td>
<td>@bread_KRumbs</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B079Y9BDLB/ref%3Datv_dl_rdr&sa=D&ust=1584803439356000&usg=AFQjCNFKqIiYGMR2CcWVS9O6ERDQneU8xw">The Disaster Artist</a></td>
<td>@GastonKelly</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80997085?source%3D35&sa=D&ust=1584803439356000&usg=AFQjCNHrLYxY1RKK8LjWzHcgcIly7L2o7w">Narcos: Mexico Season 2</a></td>
<td>@saneelprabhu</td>
</tr>
<tr>
<td><a href="https://www.youtube.com/channel/UCMmaBzfCCwZ2KqaBJjkj0fw&sa=D&ust=1584803439356000&usg=AFQjCNGBxVlpze-hzJAEEJ_gEoT1RyFlCw">Kings and Generals</a></td>
<td>@santosh79</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/81004270?source%3D35&sa=D&ust=1584803439356000&usg=AFQjCNG3XNGUQRy6qeiz-Wu-_otZtZtajQ">Dawn Wall</a></td>
<td>@tnorthcutt</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B082L2ZCZ1/ref%3Datv_dl_rdr&sa=D&ust=1584803439357000&usg=AFQjCNHCAQ8a9dnDOGiNmvj0LeX0vvGf9A">Uncut Gems</a></td>
<td>@MAustin_4249</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80996601?source%3D35&sa=D&ust=1584803439357000&usg=AFQjCNHLsokc7fuNDdI-9kMisEk1XF_d3A">Love is Blind</a></td>
<td>@MelissaZhang13</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/dp/B084SDJ2ST/?ref%3DDVM_US_TVOD_PS_G_TIS_032020NBCU%7Cc_426690510855_m_-dc_s__&sa=D&ust=1584803439357000&usg=AFQjCNGuDLS42psCVSPoua4Fblc0hkm4Zg">Invisible Man</a></td>
<td>@restudio101</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80073823?source%3D35&sa=D&ust=1584803439357000&usg=AFQjCNFMrvSB5HdfZTxqyejd_htrGhp1jg">Room</a></td>
<td>@FurqanAmin</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/Test-New-Era-Australias-Team/dp/B085FQCDFQ&sa=D&ust=1584803439357000&usg=AFQjCNGS7P4ImCLzXrXrC5IITYY3yBTP-A">The Test</a></td>
<td>@hii_vad</td>
</tr>
<tr>
<td><a href="https://www.hulu.com/series/c9d3b601-54db-42d1-a1ed-8950cea491b1&sa=D&ust=1584803439357000&usg=AFQjCNG0vFZPUJ76CrPF-eUrVAFSPY2xDA">Killing Eve</a></td>
<td>@ImNotJK</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B01B1H0TBU/ref%3Datv_dl_rdr&sa=D&ust=1584803439357000&usg=AFQjCNENwcMtVdCDCO03CZ327OL-SyfM0A">Downton Abbey</a></td>
<td>@vegardstikbakke</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/80190519?source%3D35&sa=D&ust=1584803439357000&usg=AFQjCNHFcSoh_GtABk_hEtX-Dpt_PhLSKg">Giri/Haji</a></td>
<td>@louw_debeer</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B07RCVDTB7/ref%3Datv_dl_rdr&sa=D&ust=1584803439358000&usg=AFQjCNGdO4Su9NvoEB5EyM9Uj79_HYes2Q">Sneaky Pete</a></td>
<td>@adithaurn21</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B00BZBF35K/ref%3Datv_dl_rdr&sa=D&ust=1584803439358000&usg=AFQjCNHUAvwCzgxH-4aOCCGjXo9tG6g9sA">Into The Wild</a></td>
<td>@Vin1515</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/81039393&sa=D&ust=1584803439358000&usg=AFQjCNFGZDLiJohfkB9zw8g8By3uGAr7rw">Cheer</a></td>
<td>@aaron_luckie</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B01D86F8Z4/ref%3Datv_dl_rdr&sa=D&ust=1584803439358000&usg=AFQjCNHQSha-zKsL0kdKJ6RMlz-p8Wwscg">Drunken Master</a></td>
<td>@JesperBylund</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B081PQTMG2/ref%3Datv_dl_rdr&sa=D&ust=1584803439358000&usg=AFQjCNFWmQlCZlOa2ySHq9WgGtG39a02ZQ">Honey Boy</a></td>
<td>@ponteasi</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/70242081?source%3D35&sa=D&ust=1584803439358000&usg=AFQjCNGg5tVkTuBN3QO6qp9whZzZmzgOLQ">Arrow</a></td>
<td>@sohilgupta</td>
</tr>
<tr>
<td><a href="https://www.netflix.com/title/70143836?source%3D35&sa=D&ust=1584803439358000&usg=AFQjCNFeZkZaLH8mcEWpRn7_n61AAtJZ7A">Breaking Bad</a></td>
<td>@juliancanderson</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/Making-Mob-Chicago/dp/B07G8RSX5W&sa=D&ust=1584803439359000&usg=AFQjCNFyuDU2IVEahaXHb7TnOfPB3ZqiAQ">Making of a Mob: Chicago</a></td>
<td>@Dhruvbs</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B07YM26GDX/ref%3Datv_dl_rdr&sa=D&ust=1584803439359000&usg=AFQjCNHZT2jcCeBtVS1L0qPVhhamcCJPow">Parasite</a></td>
<td>@andreimaxwel</td>
</tr>
<tr>
<td><a href="https://www.amazon.com/gp/video/detail/B00BZA7KOS/ref%3Datv_dl_rdr&sa=D&ust=1584803439359000&usg=AFQjCNEUX8nd5qQZPQ5i0bsTd7mYwnw4JQ">Contagion</a></td>
<td>@mnalpha2019</td>
</tr>
</tbody>
</table>
Sat, 21 Mar 2020 17:00:00 +0000Sat, 21 Mar 2020 17:00:00 +0000https://danromero.org/what-to-watch-via-twitter.htmlDan RomeroCrowd-sourced recommendations from Twitter on what to watch.Jekyll linklog<p>I have been a <a href="https://daringfireball.net/">Daring Fireball</a> reader for the last 15 years. Besides being the epitome of a <a href="https://danromero.org/how-this-website-works.html">text-focused personal site</a>, one feature that I love about DF is the <a href="https://daringfireball.net/2004/06/linked_list">linklog</a>.<sup id="fnref:1" role="doc-noteref"><a href="#fn:1" class="footnote" rel="footnote">1</a></sup> It’s a clever solution for short posts about links: rather than have the title of the post point to an intra-site permalink (e.g. Tyler Cowen’s daily <a href="https://marginalrevolution.com/marginalrevolution/2020/02/friday-assorted-links-250.html">assorted link posts</a> or <a href="https://marginalrevolution.com/marginalrevolution/2020/02/a-central-bank-digital-currency-is-not-a-good-idea-redux.html">individual link with commentary posts</a>), DF’s linklog posts point to the URL of the link being discussed.</p>
<p>Posts are usually 1) a link as the post’s title, 2) an excerpt from said link, and 3) a snippet of commentary. Occasionally, a list post will turn into a <a href="https://daringfireball.net/linked/2020/02/19/larry-tesler-rip">mini-essay</a>; other times, the commentary will be a <a href="https://daringfireball.net/linked/2011/05/10/8-point-5-big-ones-jiminy">single sentence</a>. Think of it as a <a href="https://help.twitter.com/en/using-twitter/how-to-retweet">retweet with comment</a> on a domain you control.</p>
<p>As a reader, it’s a great UX—especially in an RSS reader. When you open the link in a browser, it opens to the actual link, not the link post. This also works with Instapaper—it saves the destination link, not the commentary. That said, there are many times where I get the gist of the link from the title and excerpt without having to click through. Come for the links, stay for the commentary.</p>
<p>Unfortunately, most blogging platforms don’t natively support this format. There’s a post about <a href="http://octopress.org/docs/blogging/linklog/">linklogs running on Octopress</a>, but the project hasn’t been updated since 2015 and it’s not the vanilla version of <a href="https://help.github.com/en/github/working-with-github-pages/setting-up-a-github-pages-site-with-jekyll">Jekyll that runs on GitHub Pages</a>. I found another post from 2015 about <a href="https://mikebuss.com/2015/01/27/linklogs-with-jekyll/">DF-style linklogs on Jekyll</a>, but it wasn’t 100% clear how to get this working with GitHub Pages without breaking the RSS feed. So I wrote my own implementation.<sup id="fnref:2" role="doc-noteref"><a href="#fn:2" class="footnote" rel="footnote">2</a></sup></p>
<hr />
<h2 id="jekyll-linklogs-on-github-pages">Jekyll linklogs on GitHub Pages</h2>
<p>For each post, you will need a custom variable in your <a href="https://jekyllrb.com/docs/front-matter/">front matter</a> where you will put your link. I chose the variable <code class="language-plaintext highlighter-rouge">link</code>, but you can change this. Careful not to use a reserved variable like <code class="language-plaintext highlighter-rouge">url</code> as it won’t work.</p>
<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>---
layout: post
title: Paul Graham on how to write usefully
date: 2020-02-19
link: http://paulgraham.com/useful.html
---
</code></pre></div></div>
<p>In your post.html (or equivalent) <a href="https://jekyllrb.com/docs/step-by-step/04-layouts/">layout</a>, you want to add an if statement to correctly render the title with the external URL if a link post.</p>
<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code><h1>
{% if page.link %}
<a href="{{ page.link }}">
{{ page.title }}
</a>
{% else %}
<a href="{{ page.url }}">
{{ page.title }}
</a>
{% endif %}
</h1>
</code></pre></div></div>
<p>Finally, for the RSS feed to work like Daring Fireball’s, you’ll want to save the following custom <code class="language-plaintext highlighter-rouge">feed.xml</code> template in your top-level directory.</p>
<script src="https://gist.github.com/danromero/7cf2e5717eede551700801af60cb0aa2.js"></script>
<p>The template leverages <a href="https://jekyllrb.com/docs/liquid/">Liquid</a> and works with GitHub Pages. I added a 📎 (<code class="language-plaintext highlighter-rouge">&#128206;</code> in HTML Unicode) as a prefix before link posts. Feel free to swap for a different character or remove completely.</p>
<p>Happy hyperlinking.</p>
<hr />
<div class="footnotes" role="doc-endnotes">
<ol>
<li id="fn:1" role="doc-endnote">
<p>The author of Daring Fireball, John Gruber, is also the creator of <a href="https://daringfireball.net/projects/markdown/">Markdown</a> (which I’m using to write this post). <a href="#fnref:1" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
<li id="fn:2" role="doc-endnote">
<p>I’m not sure if I will use a linklog on this site vs. <a href="https://twitter.com/dwr">Twitter</a>. <a href="#fnref:2" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
</ol>
</div>
Fri, 21 Feb 2020 17:00:00 +0000Fri, 21 Feb 2020 17:00:00 +0000https://danromero.org/jekyll-linklog.htmlDan RomeroHow to make a Daring Fireball-style linklog with Jekyll.Improved Anki stylesheets<p>I’ve long been a fan of <a href="https://apps.ankiweb.net">Anki</a> as a general purpose tool for learning new concepts. Michael Nielsen has a <a href="http://augmentingcognition.com/ltm.html">good overview</a> of using Anki to augment long-term memory.</p>
<p>Despite it being useful free software overall, Anki’s UI is not its strong point. I find the default font size for cards is too small and dislike the lack of clear visual differentiation between questions and answers.</p>
<p>I recently discovered that the Anki card templating system is HTML and CSS-based, and thus fairly straightforward to create custom styles for cards.</p>
<p>Since most of the deck content is text, I was able to leverage the text-focused <a href="https://danromero.org/how-this-website-works.html">design of this site</a> for a quick improvement for the legibility and aesthetics of my Anki cards. It turned a default card from something like this…</p>
<p><img src="/assets/posts/anki/1.png" alt="1" /></p>
<p>…into something like this:</p>
<p><img src="/assets/posts/anki/2.png" alt="2" /></p>
<p>Improvements include: larger font size, improved typeface in San Francisco, left-aligned text for longer, multiline answers, off-white background, and subtle improvements to the visual weight of the <code class="language-plaintext highlighter-rouge"><hr></code> tag.</p>
<p>Below are instructions for how to set this up for yourself. The sample deck in the the example is 100% text-based. You could easily modify the design to incorporate images (just another class or <code class="language-plaintext highlighter-rouge"><span></code>).</p>
<hr />
<h2 id="instructions">Instructions</h2>
<ol>
<li>Open up the Anki Mac client.<sup id="fnref:1" role="doc-noteref"><a href="#fn:1" class="footnote" rel="footnote">1</a></sup></li>
<li>Open the deck you want to style by clicking the name of the deck and then the <code class="language-plaintext highlighter-rouge">Study Now</code> button.</li>
<li>In the lower left corner click on the <code class="language-plaintext highlighter-rouge">Edit</code> button.</li>
<li>In the top left corner click on the <code class="language-plaintext highlighter-rouge">Cards...</code> button.</li>
<li>Add the below to each of the 3 sections of the <code class="language-plaintext highlighter-rouge">Card Types</code> window.</li>
</ol>
<p><img src="/assets/posts/anki/3.png" alt="3" /></p>
<p>In the front template section, I used an <code class="language-plaintext highlighter-rouge"><h1></code> wrapped around the <code class="language-plaintext highlighter-rouge">word</code> field for the front of the card.<sup id="fnref:2" role="doc-noteref"><a href="#fn:2" class="footnote" rel="footnote">2</a></sup></p>
<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code><h1>{{word}}</h1>
</code></pre></div></div>
<p>For the styling section, I used the following CSS.</p>
<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>.card {
font-family: -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif;
font-size: 2em;
background-color: #fafafa;
max-width: 40rem;
padding: 2rem;
margin: auto;
color: #222;
}
</code></pre></div></div>
<p>And for the back template, I repeated the <code class="language-plaintext highlighter-rouge">word</code> field and separated it from the <code class="language-plaintext highlighter-rouge">definition</code> field by an <code class="language-plaintext highlighter-rouge"><hr></code>.</p>
<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>{{FrontSide}}
<hr />
{{definition}}
</code></pre></div></div>
<hr />
<div class="footnotes" role="doc-endnotes">
<ol>
<li id="fn:1" role="doc-endnote">
<p>I haven’t tested this on Windows or Linux. I don’t think editing styles works on mobile. <a href="#fnref:1" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
<li id="fn:2" role="doc-endnote">
<p>The fields in this deck are <code class="language-plaintext highlighter-rouge">word</code> and <code class="language-plaintext highlighter-rouge">definition</code>. <a href="#fnref:2" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
</ol>
</div>
Wed, 19 Feb 2020 17:00:00 +0000Wed, 19 Feb 2020 17:00:00 +0000https://danromero.org/improved-anki.htmlDan RomeroA few quick improvements for more legible Anki cards.How this website works<h2 id="github-pages">GitHub Pages</h2>
<p>Hosting is on <a href="https://pages.github.com">GitHub Pages</a>. My rationale: I already had a GitHub premium account and thought the integrated version control support for both the site’s design and content was compelling.</p>
<h2 id="jekyll">Jekyll</h2>
<p>The content management system is <a href="https://jekyllrb.com">Jekyll</a>. I chose to use a static site generator over a hosted CMS for several reasons:</p>
<ul>
<li><strong>Less overhead:</strong> in previous versions of my personal website, I had used <a href="https://www.movabletype.org">Movable Type</a>, <a href="https://textpattern.com">Textpattern</a> and <a href="https://wordpress.org/">WordPress</a>. And while each had its own benefits, I felt like I was spending too much time fiddling around with settings, plug-ins and upgrades instead of posting. Also, I’ve found most CMS design templating systems to have steep learning curves making design customization more time-intensive.</li>
<li><strong>No database:</strong> I like having all of my writing saved in a git repository in offline, searchable Markdown files.</li>
<li><strong>Future-proof:</strong> since the output of static site generators are plain HTML files rather than CMS server-generated pages, it felt like the most future-proof approach.<sup id="fnref:1" role="doc-noteref"><a href="#fn:1" class="footnote" rel="footnote">1</a></sup></li>
</ul>
<p>As for why Jekyll over other static site generators (like <a href="https://gohugo.io">Hugo</a> or <a href="https://blog.getpelican.com">Pelican</a>): the excellent <a href="https://jekyllrb.com/docs/github-pages/">GitHub Pages Jekyll support</a>. I can upload Markdown files and GitHub takes care of all generating. One downside of using Jekyll was the lack of native mobile apps for iPhone and iPad, but I don’t post frequently enough that this is a major issue, and in a pinch GitHub’s mobile website works well enough for quick edits.<sup id="fnref:2" role="doc-noteref"><a href="#fn:2" class="footnote" rel="footnote">2</a></sup></p>
<h2 id="custom-theme">Custom Theme</h2>
<p>The Jekyll theme for this website is custom. I originally started with an out-of-the-box Jekyll theme called <a href="https://jekyll.github.io/minima/">Minima</a> but it felt too generic. After an underwhelming <a href="https://www.google.com/search?&q=jekyll+themes">search</a> for a better Jekyll theme, I decided to build my own.</p>
<p>My goals for the design were as follows:</p>
<ul>
<li><strong>Text-focused:</strong> I’ve been a fan of a number of text-focused personal sites<sup id="fnref:3" role="doc-noteref"><a href="#fn:3" class="footnote" rel="footnote">3</a></sup> for a while and most of my output will be text not visuals. Additionally, this made it easier to make the design responsive without too much effort.</li>
<li><strong>Fast-loading:</strong> especially on mobile. The text-focus accomplished most of this, but I explicitly tried to minimize slower-loading dependencies like custom fonts. I also figured fewer dependencies meant it would be less likely to break and more future-proof.</li>
<li><strong>No UI complexity:</strong> a lot of standard responsive themes add in fancy features like <a href="https://medium.muz.li/3-good-reason-why-you-might-want-to-remove-that-hamburger-menu-from-your-product-69b9499ba7e2">hamburger menus</a> that I think are unnecessary for straightforward personal websites.</li>
<li><strong>No search:</strong> Google with a “<a href="https://www.google.com/search?q=site%3Adanromero.org">site:danromero.org</a>” is more effective.</li>
<li><strong>No comments:</strong> like <a href="https://avc.com/2020/01/avc-3-0/">Fred Wilson</a>, I think comments are best on Twitter.</li>
</ul>
<p>Since I wanted to minimize dependencies, I started with a blank CSS file. I thought this <a href="https://perfectmotherfuckingwebsite.com">perfect version</a> of <a href="https://motherfuckingwebsite.com">MFW</a> was pretty close to my ideal text-focused design. Using that as a base, I removed and added some declarations, tweaked the typography setting to something I found visually suitable on both desktop and mobile, and that was it.</p>
<p>As for the <a href="https://jekyllrb.com/docs/layouts/">layouts</a> and <a href="https://jekyllrb.com/docs/includes/">includes</a>, I simplified them as much as possible.</p>
<p>You can find an open source version of the theme on <a href="https://github.com/danromero/clio">GitHub</a>.</p>
<h2 id="ulysses">Ulysses</h2>
<p><a href="https://ulysses.app">Ulysses</a> is my Markdown editor of choice on macOS and iOS. (I will write about this setup in more detail at some point.)</p>
<h2 id="open-graph">Open Graph</h2>
<p>Twitter’s default way of displaying a URL in a tweet is fairly bland. Inspired by Daniel Gross, I’ve been manually making images for my posts in Keynote, exporting as a JPEG and then including the image URL in the <a href="https://jekyllrb.com/docs/front-matter/">front matter</a>. The front matter image URL is then automatically included via a <a href="https://jekyllrb.com/docs/liquid/">Liquid</a> variable in the header.html <a href="https://jekyllrb.com/docs/includes/">include</a> for my Jekyll site. Twitter OG support has <a href="https://developer.twitter.com/en/docs/tweets/optimize-with-cards/guides/troubleshooting-cards">a few specific quarks</a>. It works in iMessage, WhatsApp, Telegram, too.</p>
<p>A tip: Twitter will cache the first version of the OG content for a given URL. So if you make changes to content or the OG image, you have to manually refresh the cache using the <a href="https://cards-dev.twitter.com/validator">Twitter card validator</a>. Just drop in the URL of your post and Twitter’s servers will re-cache the latest content.</p>
<h2 id="hover">Hover</h2>
<p><a href="https://www.hover.com">Hover</a> is my domain registrar.<sup id="fnref:4" role="doc-noteref"><a href="#fn:4" class="footnote" rel="footnote">4</a></sup></p>
<h2 id="google-analytics">Google Analytics</h2>
<p><a href="https://analytics.google.com">Google Analytics</a> for traffic stats. Passively looking to change to something more lightweight that works well with GitHub Pages and Jekyll.</p>
<div class="footnotes" role="doc-endnotes">
<ol>
<li id="fn:1" role="doc-endnote">
<p>I believe we will still be consuming most text on the internet via HTML in the next 10 years. <a href="#fnref:1" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
<li id="fn:2" role="doc-endnote">
<p>I found getting Jekyll set up in local macOS environment to be a bit tricky. If you have a guide that’s current as of February 2020, feel free to share with me and I’ll link to it here. <a href="#fnref:2" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
<li id="fn:3" role="doc-endnote">
<p>Favorites include: <a href="https://www.gwern.net">Gwern</a>, <a href="https://guzey.com">Alexey Guzey</a>, <a href="https://danwang.co">Dan Wang</a>, <a href="https://kwokchain.com">Kevin Kwok</a>, <a href="https://florentcrivello.com">Florent Crivello</a>, <a href="https://devonzuegel.com">Devon Zuegel</a>, <a href="https://patrickcollison.com">Patrick Collison</a>, <a href="http://sriramk.com">Sriram Krishnan</a>, <a href="https://dcgross.com">Daniel Gross</a>, <a href="https://norvig.com">Peter Norvig</a>, and <a href="https://nintil.com">Nintil</a>. <a href="#fnref:3" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
<li id="fn:4" role="doc-endnote">
<p>If you are using GitHub Pages for hosting, be sure to enable HTTPS on your GitHub Pages settings page. Otherwise, both Chrome and Safari will display a “site not secure” warning. When setting this up, I ran into some DNS caching issue when trying to test the HTTPS URL for the site. The best solution was to a) try from another device and/or Internet connection (e.g. my iPhone cellular data vs. Wi-Fi) b) go do something else for 30-60 minutes and let the cache expire. 🤷♂️ <a href="#fnref:4" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
</ol>
</div>
Mon, 10 Feb 2020 17:00:00 +0000Mon, 10 Feb 2020 17:00:00 +0000https://danromero.org/how-this-website-works.htmlDan RomeroAn overview of how danromero.org is built and runs.January 2020 links<p>Here’s a mostly comprehensive list of the links I found interesting in January 2020.</p>
<h2 id="technology-startups-progress">Technology, Startups, Progress</h2>
<p><a href="https://cdixon.org/2020/01/17/inside-out-vs-outside-in">Inside-out vs. outside-in technologies</a> from Chris Dixon. Alex Danco on <a href="https://alexdanco.com/2020/01/23/social-capital-in-silicon-valley/">social capital</a> in Silicon Valley. Paul Graham essays on <a href="http://paulgraham.com/noob.html">noobs</a> and <a href="http://paulgraham.com/fh.html">haters</a>. Post about <a href="https://kwokchain.com/2020/01/23/underutilized-fixed-assets/">underutilized fixed assets</a> from Kevin Kwok. Julian Lehr on <a href="https://julian.digital/2020/01/26/newsletters-and-alternative-trade-routes/">newsletters, Telegram and blogs</a>; a <a href="https://twitter.com/lehrjulian/status/1221466830964916230?s=20">list of Telegram blogs</a>. Nintil’s 13,000+ word <a href="https://nintil.com/longevity/">Longevity FAQ</a> (and the <a href="https://nintil.com/longevity-making-of/">making of it</a>). Florent Crivello wrote about <a href="https://florentcrivello.com/index.php/2020/01/06/how-apple-sells-software-at-hardware-prices/">how Apple sells software at hardware prices</a>. <a href="https://medium.com/@juliadewahl/how-to-start-angel-investing-8f2eb779e96f?source=friends_link&sk=3d3dee8c09e4945264f444efb05ee17f">How to start angel investing</a> from Julia DeWahl. Dan Wang’s <a href="https://danwang.co/2019-letter/">annual letter</a>. The <a href="https://twitter.com/alexeyguzey/status/1212953763192999936?s=21">best tweets</a> in 2019 from Alexey Guzey.</p>
<p><a href="https://twitter.com/ludoviclandry/status/1222596449923289088?s=21">A claim</a> that SpaceX’s Starlink is now the largest satellite constellation in orbit. Why this <a href="https://sneak.berlin/20200129/starlink/">matters</a>; another <a href="https://caseyhandmer.wordpress.com/2019/11/02/starlink-is-a-very-big-deal/">viewpoint</a>. Bonus: <a href="https://james.darpinian.com/satellites/?special=starlink">track</a> Starlink satellites.</p>
<p><a href="https://twitter.com/dsa/status/1212459166654033920?s=21">Idea</a> for a recruiting software startup from Russ d’Sa (from 2008!). A <a href="https://twitter.com/balajis/status/1219089741490147328?s=21">RescueTime 2.0 idea</a>. Enterprise <a href="https://aashay.substack.com/p/b2b-and-enterprise-product-ideas">product ideas</a>.</p>
<p>A list of companies that “<a href="https://twitter.com/balajis/status/1210312801572524032?s=21">got big slow</a>” from Balaji. First Round Capital says the time between <a href="https://twitter.com/danprimack/status/1222646093453774853">1st contact and term sheet</a> has decreased by an order of magnitude sine 2004. Tony Fadell sent a development timeline for the <a href="https://twitter.com/patrickc/status/1216477318434050048?s=21">original iPod</a> to Patrick Collison (and a <a href="https://twitter.com/altimor/status/1218113931308347392?s=21">historical iPod sales chart</a>). Also Apple: <a href="https://twitter.com/seanrose/status/1217554702054768640?s=21">rebuilding the iOS phone app</a> from Sean Rose.</p>
<p>Florent Crivello’s thread on <a href="https://twitter.com/Altimor/status/1221116963700858884?s=20">progress in atoms</a>. <a href="https://academic.oup.com/past/advance-article/doi/10.1093/pastj/gtz032/5686413">The US as a “developing nation”</a> paired with a Dan Wang <a href="https://twitter.com/danwwang/status/1219985300908150785">thread</a>. <a href="https://twitter.com/justindross/status/1217175210794733568?s=21">Prop 13 commentary</a> and the upcoming <a href="https://nymag.com/intelligencer/2019/08/2020-property-tax-battle-in-california-could-be-epic.html">ballot measure</a> to exclude commercial property from Prop 13.</p>
<p>A <a href="https://twitter.com/antoniogm/status/1215632222700462080?s=21">good take on a dumb article</a> about an irrelevant Silicon Valley micro-trend. A <a href="https://twitter.com/austen/status/1211144183018246144?s=21%0A">continuous glucose monitoring thread</a>. A cogent <a href="https://twitter.com/post_market/status/1216100378011324417?s=21">Casper S-1 take</a>. <a href="https://twitter.com/chetanp/status/1210957678048006145?s=21">Instant Pot facts</a>. A <a href="https://twitter.com/Evanish/status/1212767967370448898">product management thread</a>. The <a href="https://twitter.com/ryangraves/status/1214276462481555457?s=21">most valuable startup tweet of all time</a>?</p>
<h3 id="climate">Climate</h3>
<p>Michael Nielsen thread on <a href="https://twitter.com/michael_nielsen/status/1204129299369877504">personal behavior in response to climate change</a> and a followup <a href="https://twitter.com/michael_nielsen/status/1211394469133570049?s=20">tweetstorm</a>. Ryan Orbuch’s <a href="https://docs.google.com/document/d/1DfZrTdy4cKb-VN7e_-E4oNe6WZpqVnvVGkzf8jMYTjs/edit">Negative Emissions Reading List</a>. <a href="https://twitter.com/michael_nielsen/status/1211394497419984896?s=21">Solar prices</a> dropping, <a href="https://arstechnica.com/science/2019/12/we-calculated-emissions-due-to-electricity-loss-on-the-power-grid/">electrical grid power loss</a> and Tesla’s <a href="https://twitter.com/noahpinion/status/1210212877577183234?s=21">impact on battery prices</a>. Microsoft <a href="https://blogs.microsoft.com/blog/2020/01/16/microsoft-will-be-carbon-negative-by-2030/">going carbon neutral</a>. Lastly, <a href="https://twitter.com/michael_nielsen/status/1215345154728456192?s=21">Churchill on nuclear power</a> in 1933(!).</p>
<h3 id="old-decade-new-decade">Old decade, new decade</h3>
<p>SSC did a <a href="https://slatestarcodex.com/2020/01/08/what-intellectual-progress-did-i-make-in-the-2010s/">personal review of the 2010s</a>. What the <a href="https://www.theatlantic.com/politics/archive/2019/12/us-intelligence-predictions-2020/604273/">2004 American intelligence community thought 2020</a> would be like; a <a href="https://news.ycombinator.com/item?id=1027093">2010s prediction thread</a> on Hacker News.</p>
<p>As for 2020 predictions, three that were a bit more under-the-radar: Jeff Lonsdale’s <a href="https://unpleasantfacts.com/some-2020-predictions">2020 predictions</a>, Zach Perret’s <a href="https://twitter.com/zachperret/status/1220072715123474432?s=21">fintech predictions</a>, and Mike Maples, Jr. <a href="https://twitter.com/m2jr/status/1213988440905175040?s=21">thread of potential macro technology trends for the 2020s</a>.</p>
<h3 id="crypto">Crypto</h3>
<p><a href="https://www.pooltogether.com">PoolTogether</a> is an Ethereum-based “no-loss, audited savings game”, i.e. a lottery where you don’t lose your principal (or a savings account that pays out interest in a very lumpy manner). <a href="https://twitter.com/dwr/status/1217182797837651968?s=21">Zero knowledge proofs non-financial use case</a> thread. Bitcoin-backed lending <a href="https://twitter.com/max_bronstein/status/1220144290334031872?s=21">thread</a>. (Crypto lending (Bitfinex) and leverage (BitMEX, MakerDAO) markets are under-appreciated phenomena by most non-crypto people in tech.) Jesse Walden on <a href="https://twitter.com/jessewldn/status/1215393602580504576?s=21">progressive decentralization</a> for crypto companies (trend worth watching). <a href="https://www.youtube.com/watch?v=Dur918GqDIw&feature=youtu.be">The Pseudonymous Economy</a> presentation from Balaji.</p>
<hr />
<h2 id="productivity">Productivity</h2>
<p><a href="https://twitter.com/dwr/status/1222749916776108033?s=21">Suggestions</a> for getting downloaded PDFs from Mac to an iOS device. Email to Kindle and Dropbox folder set to “offline” are the most straightforward.</p>
<p>For Twitter: <a href="https://twitter.com/kchristidis_/status/1220816402694561794">remove</a> non-tweet junk, search <a href="https://twitter.com/andrewchen/status/1215024957534507008?s=21">minimum retweets</a> and <a href="https://twitter.com/posobin/status/1219004261717200896?s=21">just who you follow</a>, and you should probably <a href="https://twitter.com/arjunblj/status/1217872336394735616?s=21">follow more people</a>. Is Michael Nielsen the <a href="https://twitter.com/sriramk/status/1215051410200395784?s=21">ideal Twitter user</a>? Bonus: <a href="https://twitter.com/dwr/status/1212447241723695105?s=21">my ideal Twitter client</a>.</p>
<p><a href="https://twitter.com/altimor/status/1215398728607117316?s=21">Tips</a> for reducing stress. <a href="https://devonzuegel.com/post/unconventional-strategies-for-practicing-spanish">Unconventional strategies</a> for practicing Spanish. An <a href="http://ilya.sukhar.com/blog/an-algorithmic-solution-to-insomnia.html">algorithmic solution</a> to insomnia. Why <a href="http://www.craigkerstiens.com/2019/02/12/sql-most-valuable-skill/">SQL is underrated</a>. A <a href="https://twitter.com/eladgil/status/1220882700883509248?s=20">thread on tools for remote teams</a>. And how to write <a href="https://twitter.com/dksf/status/1213947779866869761?s=21">a clean email</a> and a <a href="https://twitter.com/danielgross/status/1219658728833634305?s=21">good investor update</a>.</p>
<hr />
<h2 id="misc">Misc</h2>
<p>Pre-order Ben Cohen’s new book on the <a href="https://twitter.com/bzcohen/status/1215676386293186560?s=21">hot hand phenomenon</a>. Devon Zuegel’s <a href="https://twitter.com/devonzuegel/status/1212414927777992705?s=21">Against the Grain review</a> (and <a href="https://slatestarcodex.com/2019/10/14/book-review-against-the-grain/">SSC’s review</a> from earlier last year). Will <a href="https://twitter.com/posobin/status/1187619062546948097?s=20">blog clubs</a> be a thing? Balaji’s <a href="https://twitter.com/balajis/status/1216195268456087552?s=21">interesting scientific websites thread</a>.</p>
<p>Lots o’ maps: <a href="https://twitter.com/ifckinglovemaps/status/1221130874487562243?s=21">map of Africa</a>, <a href="https://twitter.com/delk/status/1216780978305134596?s=21">The Histomap</a> and an <a href="https://twitter.com/poa_nyc/status/1220199103658971143/photo/1">HTTP request map</a>.</p>
<p>Claims: <a href="https://twitter.com/kankanivishal/status/1215428452528115712?s=21">2.5% of remittances</a> between US and Mexico happening over crypto rails and there are <a href="https://twitter.com/webdevmason/status/1215461095588036608?s=21">fewer natural disaster deaths</a>.</p>
<p>Josh Barro on <a href="http://nymag.com/intelligencer/2020/01/the-secret-to-a-relaxing-vacation-meticulous-planning.html">meticulous vacation planning</a> (not for me) and Dustin Curtis’ <a href="https://twitter.com/dcurtis/status/1217659328879976448?s=21">interesting hotel experiences thread</a>.</p>
<p>Mason Hartman on <a href="https://www.perell.com/fellowship-essays/whats-gone-wrong-in-schooling">what’s gone wrong with schooling</a>, a <a href="https://twitter.com/michaelxpettis/status/1215733076233310209?s=21">USSR economy thread</a>. A good <a href="https://nymag.com/intelligencer/2019/12/boris-johnson-brexit.html">Boris Johnson profile</a>. <a href="https://www.reddit.com/r/IAmA/comments/elgcxp/i_am_peter_zeihan_a_geopolitical_strategist/">Zeihan’s Reddit AMA</a>. The roaring <em><a href="https://twitter.com/antonhowes/status/1213175540611502081?s=21">1620s</a></em>. <a href="https://twitter.com/auderdy/status/1215491261123006464?s=21">Origins</a> of Vietnamese nail salons. And last but not least, <a href="https://twitter.com/lilnasx/status/1214957785718218753?s=21">Lil Nas X calling his shot</a> in January 2019!</p>
Tue, 04 Feb 2020 17:00:00 +0000Tue, 04 Feb 2020 17:00:00 +0000https://danromero.org/january-2020-links.htmlDan Romero83 links I found interesting last month.iPad at 10<p>The iPad turned 10-years old this week.</p>
<p>I use an <a href="https://www.apple.com/ipad-pro/">11-inch iPad Pro with LTE</a> with Google Fi as my primary device while traveling. Always-on internet virtually anywhere on Earth on a laptop-sized device is terrific. Last year I also found myself using the iPad as my preferred Kindle device—I love continuous scroll as a way to skim through a too-much-detail-for-a-layperson section of a dense non-fiction book.</p>
<p>Here’s a round up of some good essays looking at the iPad at 10:</p>
<ul>
<li>
<p><a href="https://daringfireball.net/2020/01/the_ipad_awkwardly_turns_10">The iPad Awkwardly Turns 10</a> by John Gruber</p>
</li>
<li>
<p><a href="https://stratechery.com/2020/the-ipad-at-10-the-ipad-disappointment-ipads-missing-ecosystem/">The Tragic iPad</a> by Ben Thompson</p>
</li>
<li>
<p><a href="https://twitter.com/stevesi/status/1221853721363013632">Tweetstorm</a> and <a href="https://medium.learningbyshipping.com/the-10th-anniversary-of-the-ipad-a-perspective-from-the-windows-team-eaca7f94c5cc">essay</a> by Steven Sinofsky</p>
</li>
<li>
<p><a href="https://dcurt.is/ipad-2020">iPad in 2020</a> by Dustin Curtis</p>
</li>
</ul>
<p>And while not a reflection on 10 years of iPad, a bonus <a href="https://paulstamatiou.com/made-on-an-ipad-pro/">in-depth iPad Pro review</a> from Paul Stamatiou.</p>
Tue, 28 Jan 2020 17:00:00 +0000Tue, 28 Jan 2020 17:00:00 +0000https://danromero.org/ipad-10-year.htmlDan RomeroThe iPad at 10-years old.Startup canon<p><img src="/assets/canon-small.jpeg" alt="bookshelf" title="bookshelf" /></p>
<p>I often get introduced to people looking to make the jump into startups and Silicon Valley. This is the reading list I send them. It’s not meant to be comprehensive. Rather, it’s meant to be a primer for many of the popular concepts and jargon you will hear working at a startup. If you have suggestions for additions, feel free to <a href="https://danromero.org/about">send me a message</a>.</p>
<hr />
<h2 id="notes-from-cs183-startups"><a href="https://blakemasters.tumblr.com/peter-thiels-cs183-startup">Notes from CS183: Startups</a></h2>
<p>Peter Thiel’s 2012 class on startups at Stanford. The notes were taken by a student, Blake Masters, and later turned into a <a href="https://www.amazon.com/dp/B00J6YBOFQ/ref=dp-kindle-redirect?_encoding=UTF8&btkr=1">book</a>. My favorite lecture is “<a href="https://blakemasters.tumblr.com/post/24578683805/peter-thiels-cs183-startup-class-18-notes">Class 9: If You Build It, Will They Come?</a>”.</p>
<h2 id="the-pmarca-archive"><a href="https://pmarchive.com/">The pmarca archive</a></h2>
<p>An archive of Marc Andreessen’s now defunct blog. My favorite post is titled “<a href="https://pmarchive.com/guide_to_startups_part4.html">The only thing that matters</a>”.</p>
<h2 id="paul-graham"><a href="http://paulgraham.com/articles.html">Paul Graham</a></h2>
<p>All of Paul Graham’s essays. My favorites are “<a href="http://paulgraham.com/ds.html">Do Things That Don’t Scale</a>” and “<a href="http://www.paulgraham.com/wealth.html">How To Make Wealth</a>”. Paul also has a good book called “<a href="https://www.amazon.com/Hackers-Painters-Big-Ideas-Computer/dp/1449389554">Hackers and Painters</a>” (originally an <a href="http://www.paulgraham.com/hp.html?utm_source=lasindias.info/blog">essay</a>).</p>
<h2 id="ben-horowitzs-e-book"><a href="https://a16z.com/2016/09/04/ben-blog-ebook/">Ben Horowitz’s e-book</a></h2>
<p>Like Marc Andreessen, Ben’s original blog no longer exists. Fortunately, his original blog posts were turned into an <a href="https://a16z.com/2016/09/04/ben-blog-ebook/">e-book</a>. My favorite post is “<a href="https://a16z.com/2011/11/13/lead-bullets/">Lead Bullets</a>”. The content was also adapted into a general management <a href="https://www.amazon.com/dp/B00DQ845EA/">book</a>.</p>
<h2 id="the-idea-maze"><a href="https://spark-public.s3.amazonaws.com/startup/lecture_slides/lecture5-market-wireframing-design.pdf">The Idea Maze</a></h2>
<p>From one the lectures of Balaji Srinivasan’s Stanford 2015 course/MOOC <a href="https://www.edcast.org/learn/startup-engineering-course-2015">CS184: Startup Engineering</a>.</p>
<h2 id="chris-dixons-selected-essays"><a href="https://cdixon.org">Chris Dixon’s selected essays</a></h2>
<p>My favorite post is “<a href="https://cdixon.org/2015/01/31/come-for-the-tool-stay-for-the-network">Come for the tool, stay for the network</a>”.</p>
<h2 id="lessons-from-keith-rabois"><a href="http://delian.io/lessons.html">Lessons from Keith Rabois</a></h2>
<p>Written down by <a href="https://twitter.com/zebulgar">Delian Asparouhov</a>. My favorite is “<a href="http://delian.io/lessons-2">How to Interview an Executive</a>”.</p>
<h2 id="videos-from-cs183b-how-to-start-a-startup"><a href="https://startupclass.samaltman.com">Videos from CS183B: How to Start a Startup</a></h2>
<p>Sam Altman’s 2014 Stanford course on startups. My favorite video is from Facebook co-founder <a href="https://www.youtube.com/watch?time_continue=1&v=CBYhVcO4WgI&feature=emb_title">Dustin Moskovitz</a>.</p>
<h2 id="high-growth-handbook"><a href="http://growth.eladgil.com">High Growth Handbook</a></h2>
<p>A lot of the content was written by Elad Gil on his <a href="https://eladgil.com">blog</a>. My favorite section is the interview with Stripe COO <a href="http://growth.eladgil.com/book/the-role-of-the-ceo/decision-making-and-managing-executives-an-interview-with-claire-hughes-johnson/">Claire Hughes Johnson</a>.</p>
<h2 id="how-to-get-rich-without-getting-lucky"><a href="https://twitter.com/naval/status/1002103360646823936">How to Get Rich (without getting lucky)</a></h2>
<p>Naval Ravikant’s tweetstorm on wealth creation. Not startup advice per se, but many of the concepts are useful for building a career in Silicon Valley.</p>
<hr />
<p>Here are some additions from suggestions on Twitter :</p>
<h2 id="the-holloway-guide-to-equity-compensation"><a href="https://www.holloway.com/g/equity-compensation">The Holloway Guide to Equity Compensation</a></h2>
<p>An in-depth resource on startup equity. If you are an early employee at a startup, be sure to learn about 83b elections and QSBS eligibility!</p>
<h2 id="mba-mondays"><a href="https://avc.com/category/mba-mondays/">MBA Mondays</a></h2>
<p>Nearly 200 weekly posts from Fred Wilson on the basics of business. My favorite post is “<a href="https://avc.com/2013/08/mba-mondays-turning-your-team/">Turning Your Team</a>”.</p>
<h2 id="aggregation-theory"><a href="https://stratechery.com/concept/aggregation-theory/">Aggregation Theory</a></h2>
<p>Ben Thompson’s framework for thinking about internet-based businesses. However, my favorite post is about Apple and hard-to-model sustaining value of <em>well-designed</em> consumer products: “<a href="https://stratechery.com/2013/clayton-christensen-got-wrong/">What Clayton Christensen Got Wrong</a>”.</p>
<h2 id="writing-a-business-plan"><a href="https://www.sequoiacap.com/article/writing-a-business-plan/">Writing a Business Plan</a></h2>
<p>Sequoia Capital’s guide to writing a startup business plan (which is useful for creating a pitch deck). Recommended for any founder pitching their startup.</p>
Fri, 24 Jan 2020 17:00:00 +0000Fri, 24 Jan 2020 17:00:00 +0000https://danromero.org/canon.htmlDan RomeroI often get introduced to people looking to make the jump into startups and Silicon Valley. This is the reading list I send them.Coinbase's pragmatic crypto culture<p><em>This post originally appeared on <a href="https://nakamoto.com/coinbases-pragmatic-crypto-culture/">Nakamoto</a>.</em></p>
<p>I worked at Coinbase from 2014 to early 2019. Over that period, I saw the company grow from a small startup with a few dozen employees and a few hundred thousand customers to a multinational operation with almost one thousand employees and tens of millions of customers worldwide. If there is a defining cultural trait that was responsible for that success it was the company’s <em>pragmatism</em>.</p>
<p>This is not a word typically associated with cryptocurrency. From the perspective of crypto natives, pragmatism means compromise and is in opposition to what crypto stands for: rejecting the centralized fiat status quo completely and replacing it with a superior, transparent, mathematically pure, decentralized system that no one entity controls.</p>
<p>Meanwhile, from the perspective of crypto outsiders (including many people, banks, and governments), anything concerning crypto is scary—no one controls it!—and decidedly not pragmatic.</p>
<p>But it is in this tension where Coinbase’s advantage lies. As a cryptocurrency company, Coinbase is built on and benefits from decentralized systems like Bitcoin. However, its primary business—a cryptocurrency brokerage—requires a strong and on-going relationship with the fiat world, including normal users, traditional financial institutions, and regulators. In order to interface with that system, it is first and foremost necessary to be pragmatic.</p>
<p>This pragmatism was most evident in Coinbase’s core products. First, we offered secure and simple crypto storage, which amounted to centrally storing decentralized currency. Second, we allowed people to purchase Bitcoin and Ether, which meant buying crypto with fiat currency. Each of these may seem like a contradiction in terms, but the demand was there. And making these two features “just work” for the greatest number of people required tradeoffs that narrowly ideological partisans of either fiat or crypto would likely not have made.</p>
<h2 id="centrally-storing-decentralized-currency">Centrally storing decentralized currency</h2>
<p>Anyone who owns cryptocurrency knows that it’s a prime target for Internet-based thieves. While the borderless and fungible nature of crypto makes it attractive, perhaps its most important feature is that cryptocurrency transactions are essentially irreversible. There’s no global reset button a government or bank can press to return stolen funds. Once crypto is gone, it is truly gone.</p>
<p>Given that cryptocurrencies can be lost or stolen without recourse, secure storage was important early on. Beginning users typically do not want to deal with the complexity of storing funds locally. Coinbase thus very quickly became a custodian of a large amount of customer funds, a role that is better understood today but seemed quite controversial in the early days of Bitcoin. Wasn’t the whole point to be your own bank, after all? Wasn’t storing coins at Coinbase defeating the point of cryptocurrency?</p>
<p>We had both a pragmatic answer to this and an ideological answer.</p>
<p>The pragmatic answer was that this is what customers wanted. Beginners often didn’t want to deal with the complexity of downloading and syncing a wallet; they just wanted to buy and store crypto. And some advanced users, like fund managers, wanted another entity with the right legal certifications to store large amounts of money on their behalf. So just from the vantage point of serving customers, Coinbase had to serve as a custodian of funds from very early on. Moreover, Coinbase didn’t just custody the funds – in most cases it retained sole root access to the private keys. This is what allowed us to send out password reset emails for the many customers who’d forgotten their password and wanted to log back in, sometimes months or years after their first crypto purchase. Password reset was a critical feature, but all of this seemed to be against crypto ideology.</p>
<p>However, there was also a long-term ideological answer: (a) providing these tools allowed beginners to eventually evolve into power users capable of custodying their funds locally and (b) crypto wasn’t necessarily about trusting no one, but more about giving you a <em>choice</em> of whom to trust. You could now choose whether to store funds on your own hard drive, or to keep them with a service like Coinbase, or to keep some at a normal bank. The advanced users who decided to self-custody (more on this shortly) kept the rest of the system honest, but perhaps you didn’t need every user to do that immediately to gain systemic benefit. And you definitely created more crypto users overall by providing storage capabilities than by offloading that to the user.</p>
<p>However justified, it was a critical imperative for Coinbase to keep decentralized currency safe in a centralized fashion. The demand for decentralized currency confounded the partisans of fiat, and the demand for centralized storage certainly surprised many partisans of crypto. But the combined demand existed, and we met it.</p>
<p>Now, of course some advanced users demanded <em>decentralized</em> storage as well. Indeed, some advanced crypto users were quick to point out that self-custody is “simple” to do. However, the same thinking was behind the “year of Linux on the desktop”, or the idea that Dropbox could be <a href="https://news.ycombinator.com/item?id=9224">trivially replaced</a> with command line FTP. Power users tend to underestimate technical complexity and undervalue convenience. And convenience is what the vast majority of people want.</p>
<p>With that said, of course Coinbase did provide tools for self-custody, both in the form of a decentralized Coinbase Wallet and in terms of the basic send/receive functionality available for all assets. We just made the pragmatic calculation that it would take time for beginners to reach that point of valuing and demanding decentralized custody, so we provided rest stops along the way.</p>
<h2 id="buying-crypto-with-fiat-currency">Buying crypto with fiat currency</h2>
<p>One of the major use cases of cryptocurrency is buying and selling it for dollars and other fiat currencies. Satoshi may not have anticipated this use case, but (to say the least) it’s a very popular one!</p>
<p>To enable the seemingly simple operation of buying Bitcoin for dollars, Coinbase needed to maintain a number of relationships to the analog financial world. It needed not just API keys, but the regulatory and partnership work to comply with the traditional financial system. Among other things that meant:</p>
<ul>
<li>
<p><strong>Compliance with the US government:</strong> Coinbase is a US-based company and was thus required to follow American rules. More ideological companies took a more aggressive approach to compliance. However, unlike taxi laws or home rentals, financial regulations are often federal laws with significant penalties. This meant pursuing and obtaining dozens of licenses across state, federal, and international jurisdictions, and working closely with regulators on our approach.</p>
</li>
<li>
<p><strong>Working with banks and payments companies:</strong> In addition to our work with regulators, Coinbase’s core business model relied on partnerships with banks and payments companies. In the US, direct access to payment rails requires a bank charter. As a new bank charter has proven <a href="https://www.housingwire.com/articles/35929-why-are-there-almost-no-new-banks-since-the-crisis/">well-nigh impossible to get</a> for many years, partnering is the next best option. However, most financial institutions are not interested in so-called money services businesses (MSBs) as customers. This is because the payments business is high volume and low margin with significant tail risk of negative news. As such, it was a high bar to obtain and maintain the partnerships that kept the banking and payment rails alive. In some cases that meant making compromises, especially around deplatforming customers that posed a regulatory or partnership risk.</p>
</li>
</ul>
<p>These were the kinds of tradeoffs we had to make to keep the fiat rails open, to allow people to make the seemingly paradoxical choice to buy digital currency with fiat currency.</p>
<h2 id="pragmatism-just-works">Pragmatism just works</h2>
<p>More than most technologies, crypto is inherently ideological. And that’s a good thing – many of the early folks joined Coinbase because they believed in those ideals. However, by leavening those ideals with a dose of pragmatism, Coinbase built something valuable that millions of people use.</p>
<p>In particular, by allowing millions of people to buy their first cryptocurrency, we increased the total addressable market for new apps and services in the emerging crypto economy. I think we made the right tradeoffs.</p>
Fri, 03 Jan 2020 17:00:00 +0000Fri, 03 Jan 2020 17:00:00 +0000https://danromero.org/coinbase-s-pragmatic-crypto-culture.htmlDan RomeroIf there is a defining cultural trait that was responsible for Coinbase's success it was the company’s pragmatism.2019 favorite RSS subscriptions<p>I spent a majority of 2019 avoiding Twitter. As a result, most of my Internet consumption originated from blogs, group messaging and email newsletters.</p>
<p>I still have a soft spot for RSS. Centralized, feed-based, algorithmic social media can often feel like fast food; RSS is the home-cooked alternative where you can dial up/down the sugar, salt and fat as you see fit.</p>
<p>Here are my favorite blogs <em>new to me</em> for 2019.</p>
<h2 id="byrne-hobart"><a href="https://medium.com/@byrnehobart/" title="Byrne Hobart">Byrne Hobart</a></h2>
<p>Byrne was my top discovery this year. The variety, quantity, and quality of his writing is impressive. His post on <a href="https://medium.com/@byrnehobart/sin-secret-series-a-4046aedf8e75?source=rss-94cdf41ea82------2">secrets</a> was my favorite. Also great were posts on <a href="https://medium.com/@byrnehobart/realist-property-rights-from-the-rec-room-to-mars-769a2b735929?source=rss-94cdf41ea82------2">Martian property rights</a>, a <a href="https://medium.com/@byrnehobart/a-modest-proposal-a-backdoor-implementation-of-free-market-industrial-policy-f5f9d88c657c?source=rss-94cdf41ea82------2">free-market industrial policy</a>, <a href="https://medium.com/@byrnehobart/what-happens-when-saudi-arabia-turns-off-the-cash-spigot-bfa1b5291e11?source=rss-94cdf41ea82------2">Saudi Arabia</a>, <a href="https://medium.com/@byrnehobart/y-combinator-not-lambda-school-is-unbundling-education-bd6fdf0c78d7?source=rss-94cdf41ea82------2">education unbundling</a>, <a href="https://medium.com/@byrnehobart/why-im-bullish-on-charter-cities-17889dc4a1ea?source=rss-94cdf41ea82------2">charter cities</a>, and <a href="https://medium.com/@byrnehobart/money-is-minted-certainty-24f17dd5cab1?source=rss-94cdf41ea82------2">money</a>.</p>
<h2 id="andrew-batson"><a href="https://andrewbatson.com/">Andrew Batson</a></h2>
<p>A blog about China and his other personal interests. My favorite post was about <a href="https://andrewbatson.com/2019/08/24/logistics-and-the-demand-for-empire/">logistics and empire</a>.</p>
<h2 id="josé-luis-ricóns-nintil"><a href="https://nintil.com/">José Luis Ricón’s <em>Nintil</em></a></h2>
<p>Independent general research blog. My favorite (in addition to his link collection posts) was his <a href="https://nintil.com/bloom-sigma/">answer</a> to Patrick Collison’s <a href="https://patrickcollison.com/questions">question</a> about <a href="https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem">Bloom’s “Two Sigma” phenomenon</a>.</p>
<h2 id="alexey-guzey"><a href="https://guzey.com/">Alexey Guzey</a></h2>
<p>Another independent general research blog. My favorite post was about <a href="https://guzey.com/how-life-sciences-actually-work/">how life sciences work</a>.</p>
<h2 id="jason-crawfords-the-roots-of-progress"><a href="https://rootsofprogress.org/">Jason Crawford’s <em>The Roots of Progress</em></a></h2>
<p>A blog about human progress. His break-out post on <a href="https://rootsofprogress.org/why-did-we-wait-so-long-for-the-bicycle">bicycles</a> was my favorite. (Jason recently went <a href="https://rootsofprogress.org/going-full-time">full-time</a> on this project!)</p>
<h2 id="the-scholars-stage"><a href="https://scholars-stage.blogspot.com">The Scholar’s Stage</a></h2>
<p>A blog about Asia, history and behavioral science. Thought-provoking post about <a href="https://scholars-stage.blogspot.com/2019/12/fissures-in-facade.html">China</a> that led to a couple of nuanced conversations with friends.</p>
Sun, 29 Dec 2019 17:00:00 +0000Sun, 29 Dec 2019 17:00:00 +0000https://danromero.org/2019-favorite-rss-subscriptions.htmlDan RomeroI spent a majority of 2019 avoiding Twitter. As a result, most of my Internet consumption originated from blogs, group messaging and email newsletters.December 2019 links<p>Only <a href="https://twitter.com/marcoarment/status/1204787952984952833">11% of Overcast users</a> stream their podcasts vs. downloading</p>
<p><a href="https://twitter.com/sbuss">Steven Buss</a> is running for Democratic County Central Committee (DCCC) in San Francisco. First SF political candidate I’ve come across who is an <a href="https://twitter.com/sbuss/status/1206042525724602368">active programmer</a>.</p>
<p>There should be more <a href="https://twitter.com/alexeyguzey/status/1206277491796647939">micro-grants of $1K</a> for independent researchers to do lit reviews.</p>
<p><a href="https://substack.com">Substack</a> feels like it’s beginning to break out. I’m personally subscribed to 10+ Substack-powered newsletters (paying for 2 of them). Zach Kanter recently <a href="https://twitter.com/zackkanter/status/1202782207959416833">quit Twitter for Substack</a>. The CEO of <a href="fast.co">Fast.co</a> is sending a public update on his company progress (in lieu of a blog?).</p>
<p>Over <a href="https://guesser.com/market/a8fcf007">$300,000 USD worth of ETH</a> bet on the UK election prediction market on Augur.</p>
<p><a href="https://twitter.com/willrinehart/status/1204794662411747329">High-speed rail may be losing money</a> in China. Thread on why the <a href="https://twitter.com/ne0liberal/status/1201586781923282949">US has struggled to deploy high speed rail</a>. Related: <a href="https://twitter.com/dkthomp/status/1202715593239126016">cost of building subway per kilometer</a> around the world.</p>
<p>Zeihan on <a href="https://twitter.com/peterzeihan/status/1205179104124760064">solar</a> and <a href="https://twitter.com/peterzeihan/status/1205179340524158976">wind</a> energy math. Also: China <a href="https://twitter.com/adam_tooze/status/1202248697028984832">uses a lot of coal</a> but 6 Chinese cities account for <a href="https://twitter.com/danwwang/status/1201740776566214657">18% of global electric vehicle sales</a>.</p>
Mon, 16 Dec 2019 17:00:00 +0000Mon, 16 Dec 2019 17:00:00 +0000https://danromero.org/december-2019-links.htmlDan RomeroLinks I found interesting last month.2019 booklist<p>I had more time for reading this year. I also traveled to several new countries and tried to read a book related to the place I was visiting.</p>
<ol>
<li><a href="https://amzn.to/35cBZvm">Against the Grain</a></li>
<li><a href="https://amzn.to/2QPueq7">Fentanyl, Inc.</a></li>
<li><a href="https://amzn.to/2tkgFqn">The Grid</a></li>
<li><a href="https://amzn.to/35gOdmG">Inside the Mind of Xi Jinping</a></li>
<li><a href="https://amzn.to/2rKeHz5">The Arabs</a></li>
<li><a href="https://amzn.to/2Fa6J5v">The Crusades through Arab Eyes</a></li>
<li><a href="https://amzn.to/2ubOISb">The Code</a></li>
<li><a href="https://amzn.to/2rQx6KQ">City of Fortune</a></li>
<li><a href="https://amzn.to/39ui7aj">The Silk Roads</a></li>
<li><a href="https://amzn.to/2tkaq64">Dominion</a></li>
<li><a href="https://amzn.to/37qzAhX">Comandante: Hugo Chavez’s Venezuela</a></li>
<li><a href="https://amzn.to/35encjC">Rise and Kill First</a></li>
<li><a href="https://amzn.to/2MIOwA8">The Italians</a></li>
<li><a href="https://amzn.to/36c8Ph4">Korea: The Impossible Country</a></li>
<li><a href="https://amzn.to/2QxHMGs">Range: Why Generalists Triumph in a Specialized World</a></li>
<li><a href="https://amzn.to/2MNh7nR">Atrocities: The 100 Deadliest Episodes in Human History</a></li>
<li><a href="https://amzn.to/2ZGmTNq">Fifty Inventions That Shaped The Modern Economy</a></li>
<li><a href="https://amzn.to/37pnaXG">Delizia: The Epic History of Italians and Their Food</a></li>
<li><a href="https://amzn.to/35ijrcW">Italian Cuisine: A Cultural History</a></li>
<li><a href="https://amzn.to/39vXaf5">VC: An American History</a></li>
<li><a href="https://amzn.to/2QggSnr">America’s Bitter Pill</a></li>
<li><a href="https://amzn.to/2tkhIqj">Amusing Ourselves to Death</a></li>
<li><a href="https://amzn.to/2thFmUz">Latin: Story of a World Language</a></li>
<li><a href="https://amzn.to/2ZEVbkf">The Sports Gene</a></li>
<li><a href="https://amzn.to/36hT08u">The Judgement of Paris</a></li>
<li><a href="https://amzn.to/2rPnAHO">Paris Reborn</a></li>
<li><a href="https://amzn.to/2ZEVvPZ">The Smartest Guys in the Room: The Amazing Rise and Scandalous Fall of Enron</a></li>
<li><a href="https://amzn.to/2rKfZKr">7 Powers</a></li>
<li><a href="https://amzn.to/35dULT8">The Story of Greece and Rome</a></li>
<li><a href="https://amzn.to/2SIRqZr">The Case Against Sugar</a></li>
<li><a href="https://amzn.to/2Qd76Td">How Asia Works</a> (re-read)</li>
<li><a href="https://amzn.to/36jUFKM">The Prize</a> (re-read)</li>
<li><a href="https://amzn.to/2thFVh9">21 Lessons</a></li>
<li><a href="https://amzn.to/2Qe4NiM">Atomic Habits</a></li>
<li><a href="https://amzn.to/2tni6Eo">The Fate of Rome</a></li>
<li><a href="https://amzn.to/36mpBdG">Forbidden Nation</a></li>
<li><a href="https://amzn.to/2SQ7F7j">The Gray Man</a></li>
<li><a href="https://amzn.to/2sF42Gj">Cash Nexus</a></li>
<li><a href="https://amzn.to/2QeHXax">Sugar</a></li>
<li><a href="https://amzn.to/37w6PAF">Delta-v</a></li>
</ol>
Mon, 16 Dec 2019 17:00:00 +0000Mon, 16 Dec 2019 17:00:00 +0000https://danromero.org/2019-booklist.htmlDan RomeroI had more time for reading this year. I also traveled to several new countries and tried to read a book related to the place I was visiting.Next steps<p><em>This post originally appeared on <a href="https://medium.com/@danromero/next-steps-ea6bd1917cbb">Medium</a>.</em></p>
<p>After 5 years, I’m leaving Coinbase at the end of the month. I’m planning to take some time to figure out what’s next, but I remain as optimistic as ever about the potential of cryptocurrency and Coinbase.</p>
<p>An increasing number of cryptocurrency entrepreneurs are quietly building the infrastructure necessary for a more open, permissionless and decentralized version of the Internet and the global financial system. Coinbase remains a key part of this story by providing the trusted and easy-to-use bridge between traditional finance and cryptocurrency.</p>
<p>I joined Coinbase when it was 20 people; it is now over 700 people. I’ve also had the privilege to work across almost every aspect of the Coinbase business—our banking partnerships, international, and time with both our consumer and institutional businesses. Through this, I’ve come to appreciate the value in working at a mission-driven company that’s willing to focus on a <a href="https://blog.coinbase.com/the-coinbase-secret-master-plan-f4d644443301">long-term strategy</a>. Staying true to a mission often requires doing hard (or even unpopular) things. But I’ve been lucky to learn first-hand that it’s those hard things that often generate the most value.</p>
<p>I want to thank <a href="https://twitter.com/brian_armstrong">Brian</a> and <a href="https://twitter.com/fehrsam">Fred</a> for taking a bet on me. I also want to thank all of my Coinbase colleagues for everything they’ve taught me over the years. I hope I’m lucky enough to work with as intellectually honest, pragmatic, and kind group of people again.</p>
Fri, 12 Apr 2019 17:00:00 +0000Fri, 12 Apr 2019 17:00:00 +0000https://danromero.org/next-steps.htmlDan RomeroAfter 5 years, I’m leaving Coinbase at the end of the month.