🚨 Mermaid has been rewritten, again. In Rust! 🧜‍♀️ Introducing Ondine. 🧜‍♀️ - 200B runtime. - Renders diagrams in ~50µs. - 1,943x smaller, 2.8x faster than Pele. - 13,467x smaller, 670x faster than Mermaid. - Still 0 dependencies.

We've unified plans across Grok, Cursor, and X Premium. Introducing The X Subscription.

ok it's official... AI-written unit tests and integration tests are empirically proven to be unhelpful. you should tell your agents to stop writing tests by themselves on the deepswe eval set, banning sonnet 5.5 high from writing any tests actually resulted in slightly higher success rate (non stat-sig), with less time and token spent (stat-sig). this is pretty hard empirical evidence across the tests that were written by the "tests allowed" baseline arm, 65% of them were unit tests, 35% were integration tests, neither bucket resulted in any improvement compared to not writing any tests at all i also picked a random sample of 44 tasks subset where i completely disabled executing even existing tests - it also did not affect success rate at all i spot checked many tests written in the baseline arm, and my intuition is that most tests are simply a repetition of the implementation agent-written tests do not add any value because both the implementation and the tests were simply the agent's interpretation of our intent. the tests aren't any more accurate than the implementation itself i suspect we can still extract some value from unit tests and integration tests if we describe them ourselves when we believe we can articulate our intent better through test cases than through requirements. but i have not proven this yet also worth noting, during deepswe eval the agent wrote almost no e2e tests (only 17, compared to 3000+ unit/integration tests written). so this analysis does not prove nor disprove the value of e2e tests - i will do another eval specifically for that

62,500 credits were just given to every legacy $200 Codex Pro account, and apparently that can translate into more than 81,000 local messages at the absolute maximum, That is actually insaneeee with GPT 6.1 Sol, the plan genuinely feels unlimited at this point. I am starting to worry that I will not even be able to burn through all these credits and my banked resets in time This is exactly why I love OpenAI so much, They are always transparent about what they are doing and they actually seem to care about their users!

I’ve said it before and I’ll say it again: Rust is a *really* bad idea for any software you need to have working a few years from now (AI generated or not), or want to continue developing into the future. Not because Rust is ugly (which… it is). And not because Rust is, overwhelmingly, a cult (again… it is). But simply because Rust is still a moving target. The language is not yet “complete”… and neither is the compiler. Changes occur often enough (and in significant enough ways) to throw serious monkey wrenches into any sizable project. Once Rust stabilizes (which could happen quickly if the Cult of Rust actually wanted it to), this problem will quickly go away. Until then I will be sticking with C. Or C++. Or, heck, any language that is more stable than Rust.