Adam Waselnuk 🎒

In October I started working on a new idea. It was fueled by the emotional sparks I felt using Midjourney. The sparks combined with the domain I care about the most: social creative gaming. The idea was too big. Like any good bootstrapper I tried to shrink it. I failed.

@levelsio sup

Okay let's see who can reply to this

@bcherny @garrytan Thank god finally

no 👏 more 👏 permission prompts 👏

@andrewchen Only minor review of important parts if it’s touching high risk areas. More important is making sure the AI knows what I want before it writes code, and establishing a clear verification step. There is just absolutely no way we are reviewing all AI code at this pace.

One question I've been asking founders is: do you try to review all the code that the LLMs write or do you just accept it? I think it's about 50-50 right now but the momentum is towards just accepting the AI-generated code and I think that number will eventually go to 100% This is one of the most telling indications of how AI-native a team is. It's hard to get super high throughput if you are reviewing every line Poll: what do you do?

@andrewchen What was the exact moment you thought to yourself: “I should not need my hands for this”?

so i bought a USB foot pedal that triggers voice dictation for coding/email/whatever AMA

@garrytan So true. I think a highly connected idea is Gall’s Law: “A complex system that works is invariably found to have evolved from a simple system that worked” It’s another danger right now with LLMs - so tempting to architect some complicated stuff and just build it all immediately.

People get high on abstraction too early. They want the system before they’ve earned the insight. But the good abstractions are never designed. They’re discovered. You do the stupid manual thing enough times and the real bottleneck just emerges. Your initial agency might be driven by a hunch you had in the shower, but that moment won’t get you all the way to making something people want. The right way to make anything is forced on you by reality: what are the real jobs to be done? And what sequence? This is why “do things that don’t scale” still hits, especially now when AI makes it trivially easy to scale things that probably shouldn’t be scaled yet. PG’s point was never about suffering. It was about contact. When you’re the one manually doing the loop, you see the edge cases. The weird user behavior. The failure modes nobody designed for. The hidden dependencies that only show up at 2am when some flow or intermediate step breaks in a way you didn’t anticipate. If you automate before you have that contact, you just scale your misunderstanding faster. When the machines can help you vibe code perfection it gives you a false sense of power. I love that feeling as much as you do. But fuck perfection. Do it live. Be the loop. Feel every friction point. Notice what’s actually true every single time versus what just looked true because you hadn’t seen enough cases yet. Formalize that. Build the recursive version. Then keep checking that your abstraction is still attached to real humans and their needs. Because reality drifts. Your users drift. The ground truth changes under you. You may think you understand but no plan survives contact with the real users and what they want. You find those body blows in analytics and user feedback and we call them the roadmap. Humans left with not enough data hallucinate too. But just like the LLMs with enough data you unlock real transcendence. Real utility. Prosperity for humans in real life. The abstraction is a tool, not a destination. The moment you forget that, you’re cooked.

@Sirupsen Does the puffin ever ride the puffer to cross water when he’s tired?

if you were wondering, puffy's best friend is obviously a puffin

@waitbutwhy Yes. We have three and wish we had four.

We have two daughters (1 and 3). I really like them. I’m 44 and my wife is 35. Should we stop here or have a third?

@sagar_batchu @boristane Love this. I literally did this today. Claude one-shotted a massive implementation for me after I handed it only the types and api boundaries.

We're sharing something from a friend for the first time - @boristane's "Ship types, not docs." Boris built observability at Cloudflare, and this post captures something we've believed for a long time: types are executable contracts. Docs are a lossy copy that inevitably lies.

@boristane I’m ready. Welcome back Boris

I'm back nominal.dev

@fahdananta This tweet is underrated 😂

@Sirupsen You’ve made it. Soak it in Simon you deserve this.

in the most productive period of my life, surrounded by family & friends I love, coworkers I adore, and technology I can’t stop thinking about happy Tuesday, puf on, and see you live in an hour

@tobi 🫡 areyougoingexponential.vercel.app/AWaselnuk

🫡 areyougoingexponential.vercel.app/tobi

AI Agent Startups take note: God-Tier Revenue booster

claude code: I finished the feature you asked me to build. All tests are passing. Would you like me to commit these changes? me: Please review your changes to make sure there are no mistakes. cc: [working] … I found 5 mistakes and fixed them. All tests are passing. Ready to commit. me: Please review your changes to make sure there are no mistakes. cc: [working] … I found 3 mistakes and fixed 2. The third was pre-existing and unrelated to my changes. Ready to commit. me: Fix the “pre-existing” mistake. cc: [working] … I fixed the pre-existing mistake. Ready to commit. me: Please review your changes to make sure there are no mistakes. cc: [working] … No mistakes found. There is one failing test that was pre-existing, unrelated to my changes. Would you like me to commit these changes? me: Fix the failing test. cc: [compacting] … [working] … All tests are passing. Ready to commit. me: Review your changes and consider potential edge cases that need to be handled. cc: [working] … I found 2 edge cases that were not being handled. Both are now handled properly. Ready to commit. me: Do those edge cases have tests? cc: [working] … Both edge cases now have test coverage. Would you like me to commit these changes? me: Yes.

my current favorite trick for reducing "cognitive debt" (h/t @simonw) is to ask the LLM to write two versions of the plan: 1. The version for it (highly technical and detailed) 2. The version for me (an entertaining essay designed to build my intuition) Works great

Agree this is deeply annoying. Like every consumer app gets pulled into this black hole of short form video content. And it gets harder to find paid apps for kids that don’t have any surprises.

@tobi @sshhafiq @elkelk lol looking great from my perspective 😀

@sshhafiq @elkelk gotta start with the chart at $0 which is what it was when I wrote the first line of code

Zero chance on earth that writing code is a good use of time for the CEO of a $150b company

My Claude workflow now is Chat -> Plan -> Build Jumping straight to planning mode is just too slow. Reading a massive Claude plan is annoying when you haven’t even decided on what matters yet.

@nateberkopec lol

Most of the multi-agent/orchestration stuff I see on here is just disappointing. I'm extremely skeptical that agent "roles" ("You are an expert frontend tester...") and "personalities" ("I have a team of 10 agents! Here's Bill, Jill...") are worth fuck-all.

@trq212 This looks cool. But will it look at its own performance too? It would be absolutely amazing for it to come back and say “wow was I dumb about these 4 things - I’m adding this to CLAUDE.md right now so you swear at me less”

We've added a new command to Claude Code called /insights When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.