Rourke

Some early thoughts after building real apps by myself for the first time… We built an internal tool called Conveyor It’s an app builder, and internal App Store It is connected to all of our data, context, and external data APIs I’m completely and utterly useless as an engineer, but I’m good at knowing what I want a tool to do. I’d previously struggled to make useful programs with pure CLIs. Our wrapper made it easy for me. In the first 3 days of having this tool, I’ve built several fairly complicated applications, two of which I’ve used a ton for real work. I’ve only used a couple hundred million tokens so far. Some early feelings: 1) It’s obvious to my that my companies Positive Sum and Colossus will have fully bespoke operating systems, built in house. They will manage as much of our work as possible. This is already exploding for things like research and reporting. Every business will want this for themselves. Sure we won’t built our own slack, but we will built everything that pertains specifically to our shape as a firm, which is a lot. 2) x402 protocol (which enables AI agents and users to pay for API access and digital services instantly, without accounts or subscriptions) is immediately interesting to me. Many times I’ve wished I could just stream payments for individual data points. 3) right now each loop of prompt to output takes 5 to 15 minutes. As models and ASICs (@Etched !) make this faster, it’s going to be so much more fun. Even 5 minutes makes it hard to get in the flow. Can’t wait for seconds instead of minutes. 4) it’s so much easier to design things by starting with a shitty first draft of an app and seeing what’s wrong and iterating than nailing a full design ahead of time. When I had directed the design of software before this was always maddening and slow. 5) this has made me realize that my imagination had atrophied. Use it or lose it is real. Very quickly I’m finding it easier to have good ideas by building more stuff. I encourage everyone to do the same. So fun and rewarding. 6) We need more compute

Not necessarily sure I agree with this as only positive for future generations. I think there is a lot of intangible benefit of social interaction at bars with alcohol. Moderation is key. Blowing off steam at a bar and drinking with friends can be net positive.

Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.

We've redesigned Claude Code on desktop. You can now run multiple Claude sessions side by side from one window, with a new sidebar to manage them all.

C’est le couplet le plus stylé de l’histoire

If you don't actively steer your life, comfort and normalcy will make the decisions for you. Mediocrity has a gravity that everyone succumbs to unless they are actively fighting against it day after day.

Every system -- including your own life -- inevitably decays into mediocrity unless someone fights to keep the standards high. That someone has to be you.

The longer you delay building the life you actually want, the more likely you are to normalize a weaker substitute. Drift hardens into identity faster than people realize.

You need to read more, and you need to consume less. You need to set aside time to do a workout for the mind, and you need to give it time to recover. Especially now that it's so easy for your cognitive capacity to atrophy. Refuse to become mentally obese.

its awesome how if i heard this song for the first time today i might think that its corny and it sucks but ill never know because i heard it 1394823038 times in sixth grade and it is permanently hardcoded in my dna as The Best Fucking Song Ever Made

If you want to achieve anything great, it needs to become your one true priority. The only thing on your mind. Nobody accidentally got rich from business. Nobody accidentally built a great physique. They were obsessed with it for multiple years until it became their default.

For decades, urban planners have rigorously tracked every car in New York City while completely ignoring the pedestrians. An MIT research group has finally built the first complete model of foot traffic in an American city. They took baseline counts from the Department of Transportation and mapped a routable dataset covering every pavement, crosswalk, and footpath across the five boroughs. The resulting data exposes massive flaws in how cities allocate infrastructure funding. Midtown Manhattan hits nearly 1,700 pedestrians per block per hour during peak times. Because officials see these massive raw numbers, they funnel the bulk of pedestrian safety investments directly into the city centre. The MIT model proves this bias is a mistake. Neighbourhoods in Brooklyn, Queens, and the Bronx routinely register hundreds of pedestrians per block per hour. People in these outer boroughs are walking in huge numbers, but they don't get the infrastructure to match. The model also rewrites the maths on urban safety. Governments typically rank dangerous intersections by tallying up total crashes. High-traffic areas like Herald Square or Times Square rack up lots of accidents. Planners look at those totals and assume the area is highly dangerous for walkers. The new system calculates risk on a per-pedestrian basis instead. When you divide the accidents by the millions of people walking through Midtown, the individual risk is actually very low. The true danger zones are around highway off-ramps and heavy car infrastructure in low-density areas like Staten Island. A pedestrian walking there faces a drastically higher statistical chance of being hit by a vehicle. This framework changes how urban development works. Los Angeles is already applying the model to prepare its public transit and mobility networks for the 2028 Olympics. The state of Maine is using it to evaluate 140 different towns to identify necessary safety upgrades. Planners finally have the hard data to prove what walkers have known for years. We spent the entire twentieth century designing our environment around the automobile. We finally have the tools to start building cities for people. Link to paper: nature.com/articles/s4428…

The only reliable path to extraordinary outcomes is extraordinary skill.

We're bringing the advisor strategy to the Claude Platform. Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

“The spreadsheet will become irrelevant” No. The spreadsheet is eternal. The spreadsheet paradigm IS capitalism. The two are irrevocably intertwined. We were using spreadsheets 3,000 years ago to trade oxen. We will still use them in 3,000 years Long live the spreadsheet

Learning advanced math and coding opens doors you don’t even know exist. You see opportunities others literally cannot even perceive.

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

Hey, I'm open-sourcing Clicky. Go forth into the wild and build the future of education and the future of AI interfaces, my friends. I'm happy to have given a spark. Enjoy! github.com/farzaa/clicky

a reminder that no one is coming to save you