
it’s all about preparation until it’s all about execution

🪐🫀📈

it’s all about preparation until it’s all about execution

Consolidation is needed, more on this soon 🧑🍳
What’s going to happen to open source? A prediction: Dependencies are over. The same Brotli vulnerability impacted .NET, Node, Bun, Envoy and more. Dependencies are too big of a target. When rewriting a dependency is one prompt away, why take the risk?

Only a matter of time until @nvidia chips are named after llms instead of people

CFO: chief frontier officer

Do most people not use test selection? If not why?
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

All I want is @Zai_org to drop glm 5.2 flash

Hey @thsottiaux the “g” in Downloading in the codex app is cutoff on the bottom and my ocd is kicking in


Looking back everything is obvious
Kevin Kwok @kevinakwok Apr 10

Real ones tremble at the words “Bayesian Data Analysis”
Most people with “AI/ML” in their bios don’t even know what Bayes theorem is.

Congrats 🥳
Starlette 1.0 is here!🎉 After nearly eight years, Starlette has reached its first stable release. Downloaded almost 10 million times a day, it serves as the foundation for FastAPI and the Python MCP SDK. Blog post: marcelotryle.com/blog/2026/0… Release notes: starlette.io/release-notes/#…

The real reason @astral_sh is joining OpenAI is because they’re working on a GitHub competitor and the biggest challenge @charliermarsh faced is GitHub going down. In all seriousness congrats Charlie 🥳

No one wants to put the single in singularity
Dating right now must be intense: "Do I want to go through the AI event horizon with you?"

I’m convinced all these ppl throwing ai hackathons pivoted from crypto

I’ve converted 6 people from Claude code to codex this week @sama rev share pls 🤣

📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent. Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`. Pls like/tag/RT for momentum.