Co-Founder & CEO @AltertableAI. Waking up idle data with AI. Previously VP Eng @sorare, GM & VP Eng @algolia, Platform at @exalead & NLP teacher @EPITA.
Today weโre releasing DeepSWE, a new standard for agentic coding benchmarks.
On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
there will be a blog post about this. on what this means for bun, benchmarks, memory usage, maintainability going forward, and also the literal process of doing this (it wasnโt just โclaude, rewrite bun in rust. make no mistakesโ)
this is a 960,000 LOC rewrite, the code truly works, passing the test suite on Linux and soon other platforms. e2e I started working on this 6 days ago. this wouldโve been a massive amount of work by hand.
why: I am so tired of worrying about & spending lots of time fixing memory leaks and crashes and stability issues. it would be so nice if the language provided more powerful tools for preventing these things.
Still amazed to read how many โengineersโ are mainly pressing Enter all day long. Iโm using Cursor, I plan for medium-large tasks, and I go right away with agent mode for small tasks; I answer a few questions but thatโs it. I donโt get it.
Don't just reset Codex rate limits for fun, it costs money.
Don't just reset Codex rate limits for fun, it costs money.
... but the vibes are good ...
I have reset Codex rate limits for ALL paid plans to celebrate a good week and allow everyone to build more with GPT-5.5. Enjoy