Imagine your next work meeting. Junior: We should fix the database perf problem with assembly You: I don't follow. We're talking about a stuck SELECT. We just need an index Junior: The database will be faster if we rewrite it in assembly. Omarchy is 17x faster because of assembly You: Rewriting a database is a big project, and an assembly port wouldn't change data structures. Asymptotically, a full table scan... Junior: DHH proved that coding agents work best in assembly. It's 17x faster than Rust. Should we be 17x slower than our competition? VP: Junior has a point. We need to provide the best customer experience. You: It'll take at least a year, even with AI help, to match PostgreSQL, and a perf win isn't guaranteed. Consider how Turso still has gaps in... Junior: Skill issue. Models can one shot this. Labs used reinforced learning to make models write the best code. VP: Great. On the roadmap for next week. You: ... So, do we want to add that index in the meantime? VP: Can you do it in assembly?

You are right but it also feels short-sighted? You have the most powerful tool you ever had, you have become a 1000x maker, and you can't think of how to make your stack 10x better? Yes, Rust is fast, the type system catches bugs, but there is so much beyond it. * Why not make Ruby 10x faster? * Why not make Ruby (and therefore Rails) really great at concurrency? * Why not add a banging type system to Ruby that can provide guarantees beyond Rust? * Why not embed SQLite3 into Rails with a replication protocol so you can really compress the stack beyond a single server? * How to preemptively fix most bugs from the most critical parts of Rails, such as database pools? Yes, who cares about ActiveSearch, but there are so many ways we can fundamentally improve our stacks that go beyond asking the agent to just crap out code. Phoenix is still the only framework that ships with presence, because it turns out it is deceptively a hard problem to solve correctly, but somehow all issues are solved? I understand some folks have no interest in doing any of the above, and that's fine, but then at least pass the baton to the people who want to do exactly that. PS: I say all of this with love ❤️

the openai huggingface incident, from an agents pov. (part 1)

Waymo is fucked.

hello

the art of framing

The launch of Stacked PRs is one of the biggest releases in @github history, touching almost every service we run I wanted to share some details about how we built it and everything that went into it Strap in folks, this is gonna be a long one 🧵

Terence Tao posted his ChatGPT session trying to understand the Jacobian conjecture counterexample. It's so lovely reading a slice of how his mind works, the connections he's making, etc. chatgpt.com/share/6a5fdc7a-d…

Lately I’ve been asking myself: what might artificial intelligence be good for besides answering questions and writing code? My answer is the latent spaces within AIs themselves will become a new medium for creativity. kevinkelly.substack.com/p/la…

I can finally talk about 5.6. I’ve been testing it for months and, without exaggeration, it’s the best model I’ve ever used. Fast, smart, genuinely creative, and you guessed it, they finally fixed front-end design. I haven’t needed to check the code I’ve written in two months.

I've found if you do TDD, it works: write the test first and then write the code. But if AI writes code and tests at the same time, it's useless.

Opus 4.6 dgafffff