Nick retweeted
T3 Code Orchestrator V2 is now live in nightly.
We rewrote the orchestrator that runs your agents. Here's what that gets you 🧵
guy discovers how profitable inference is
Readers added context they thought people might want to know
The screenshot's Grok calc overstates inference profits by pricing all ~217k tok/s/GPU benchmark tokens at full output rates; AgentX traces show ~99.5% are cheap cache-hit inputs.
inferencex.semianalysis.com/run/deepseek-v… huggingface.co/datasets/semia… api-docs.deepseek.com/quick_start/pr… x.com/smallmodelsmel…
Nick retweeted
I stayed up til 2am and spent $1,000 benchmarking Jev Router so you don't have to.
Performance on DeepSWE was roughly the same as GPT-6 Astra on low. It costs slightly more, and it took almost 5x longer to run.
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
Nick retweeted
Best part of AI is shattering dev's egos, the worst part of this industry.
You are not special. Your code actually sucked like everybody else's. You were never the smartest person.
The things my sales guy BIL and designer brother are doing is beyond anything I have done.
Introducing shadcn/lint. An agent-first linter for Tailwind design systems.
You define what’s allowed. When an agent breaks a rule, the error explains what’s wrong and how to fix it using your components, variants and theme.
There’s a lot you can do with this. Let me show you ↓
github.com/shadcn-ui/lint
Nick retweeted
I recently went through a translation of Musashi’s Book of Five Rings.
The introduction chronicled the evolution of swordsmanship and martial arts in general from pragmatic battlefield necessities to sports, historical curiosities, and hobbies. It was interesting to hear how in the post-WW2 occupation when martial arts were banned, Judo was represented as equivalent to western wrestling, and Kendo later to western fencing.
The poignant undercurrent for me is that I can see many programming skills following that path.
There are probably dozens of people reading this that remember hand assembling opcodes to hex and still have some magic numbers burned into their memory, but even the small group of people still programming in assembly today (hey, @FFmpeg !) don’t work at that primitive level now.
AI is making many other programming skills much less critical. We aren’t there yet, but carefully writing code completely by hand is moving from a -jitsu to a -do. Code-do? Codo?
That’s ok! The retro computing scene is delightful, full of people building and exercising old skills for the love of it.
But don’t be the out of touch Kung Fu master, heir to lifetimes of tradition, that gets mauled by an amateur MMA fighter.
Musashi would probably have been pretty enthusiastic about assault rifles.
Nick retweeted
Hey ████,
I think there is room for both.
1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking is low, it doesn’t need to be perfect.
2. Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. Luckily, the model makes it increasingly easy to do these well — run a few daily routines, use Claude Code Review, etc.
Your job is to hold the bar on code quality. If Claude’s code doesn’t meet the bar, try:
- Using the latest frontier model (Opus 5 or Fable 5.1)
- Increase effort to high or xhigh
- Invest in your CLAUDE.md and skills to succinctly teach Claude how to work in your codebase
If all else fails, steer Claude more when you work with it, or have Claude fix accumulated debt and rewrite your codebase to make it easier to work with. Or, wait for the next model.
Best,
Boris
Nick retweeted
I never use plan mode.
The main reason this was added to codex is for claude-pilled people who struggle with changing their habits.
just talk with your agent.
Nick retweeted
Вместо overflow: hidden можно использовать border-radius: inherit, чтобы фон ребёнка не вылезал за скруглённые углы родителя.
Например, так как overflow обрежет выносные элементы и т. п.
css-tricks.com/preventing-ch…
Nick retweeted
It's crazy how the tweets about Europe imploding in itself are just turning out to be true
Europe has been captured by an anti-tech degrowth mindvirus that now resorts to arresting tech founders in its borders
Completely unprecedented
Nick retweeted
Павел Дуров просто великий человек
Он построил огромный и успешный сошл нетворк проект в диктатуре — отняли
Построил ВТОРОЙ
Попытались отнять, переехал в другую диктатуру
Посетил демократическую страну, задержали менты
Это просто пиздец



































