i have seen enough proof now that using a coding agent is a deep skill
it's confusing because the people you see heavily using them produce horrible results
but that's because it's a skill! you can get better and the ceiling seems pretty high - this is very exciting to me
You might believe you should spend less time thinking about code because of AI.
I strongly disagree! We’re watching this play out live where tons of AI generated code becomes a liability.
At the end of the day, an engineer needs to be responsible / on call for code that gets shipped to production. If you don’t understand the system you’re trying to debug, you’re probably going to have a bad time.
Yes, AI can help with all of this, if you set up the proper systems. You can have agents triage prod logs, look at errors, etc. You can speed up parts of the investigation, but an engineer needs to make the call. There might be serious customer or financial implications from that change.
I expect the trend continue for trimming dependencies, vendoring code so you can modify it directly, preferring simpler systems with fewer abstractions, and spending waaaay more time thinking about system design and code maintenance.
I’ve said this before, but it’s a great time to get familiar with CS fundamentals and some of the history behind what great software looks like. Many parts will be different in the coming years as AI progresses, but also a lot more than people realize will stay the same.
Graphql is genuinely the most retarded idea ever. There used to be an entire career around graphql
Honestly the best part about automating programmers is that I don't have to hire people, which means that I don't have to tolerate bad engineering decisions
No-human-code-allowed projects, are nicier and much more maitainable.
Agents can actually follow strict guidelines and rules you set unlike humans who find bad shortcuts because they are lazy.
No need to compromise or waste time convincing egos that solution X is better.
@rauchg just built my first ios app 100% with ai agents https://t.co/I2sR3c6tEz, used claude code opus 4.7
still offline only, working on the server now
Small update to my polymarket client "login" without PK. You can search polymarket accounts and "impersonate" them. It's read-only obviously.
You can see their positions in markets, but you can't see not open orders, and soon you'll be able to see their portfolio and current usdc available.
🚨 BREAKING: Someone just open-sourced software that sees you through walls using only WIFI signals.
it’s called WiFi-DensePose. It maps your exact body pose in real-time. no cameras. no sensors. just your living room router.
100% Open Source.
Not knowing how to code giving you an advantage is absolute nonsense.
The more you understand, the better your prompts, the better the feedback you give, the better product you ship.
What will change is that the intricacies of syntax, compilers, module systems, the finer details of type systems, won’t matter as much to everyone.
But you should absolutely understand how the pieces fit together. From syscall to pixels. Learn how data flows, because you’ll be able to secure your systems. Learn about performance, because you’ll be able to push your agent further. Learn about APIs, because they determine how to integrate systems. Learn about how systems fail, because you’ll be able to make reliable programs.
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.
the security guy had a poor "doorman tie" and let the other guy have an underhook, then he apparently tries to do a koshi-guruma take down, but has no base, then the other guy counters with a tani-otoshi sacrifice throw and gets to side control + head and arm control
🚨BREAKING: Video of the Democratic mayor of San Francisco is going viral after he calmly walked away while his security detail was being attacked.
Mayor Daniel Lurie is seen watching his security officer struggle with a man, then turning and walking away as the officer is slammed to the ground, hits his head on the pavement, and is left bleeding.
I think if I had a project with a single 40k line file my head would explode or I would constantly freeze, and that's probably why I'm still poor and I can't make it in indie hacking
One of my projects, uses a custom swift web framework I built, it is pretty easy to add new features to the server application and to maintain the code, but it does have a bunch of boilerplate, and all the code is split in many small targets.
It is pretty reliable, but not very productive, for example, to add a endpoint I need to:
- Add a new enum case for the route (for type safe routes)
- Add a new parser for that route (for bridging http request with that enum case)
- Create a new handler for the route
- Call the handler
That's just to get started, it's annoying, but it's reliable since there is no magic anywhere, just enum switches and function calling.
Anyway, that slows me down a lot compared to using traditional web frameworks, but I just wrote some claude skill to move faster on that part, and feeling it might give me a huge productive boost, let's see how it goes.
Added a few small enhancement to the chart:
1. The Y axis showing the value in cents
2. Added outcome % chance to each item in the legend
3. The legend items sorted by % chance
Added a few small enhancement to the chart:
1. The Y axis showing the value in cents
2. Added outcome % chance to each item in the legend
3. The legend items sorted by % chance