From the archive
Wednesday, 14 October
Folded from 15 sources that day.
Sorted by quality and by how many sources covered it, the same for everyone.
-
The 2026 Maintainers Summit
Kernel maintainers discussed the Sashiko patch-review bot, LLM-assisted contributions, and the flood of security patches. They also raised how Linus Torvalds's eventual succession should be planned.
-
What Do We Do When We Read The Code?
After an LLM wrote three tests that could never fail, the author questions how much generated code is worth reading. He argues that teams will never read all of it, and that review habits and tooling must change.
-
Uber’s AI infra, from the inside
Uber Distinguished Engineer Uday Kiran Medisetty walks through the 20+ internal developer tools, including Slate and DevPods. He covers background agents, code review changes, token costs, and productivity measurement.
-
Amp puts AI agents to work beyond code with OpenAI models
OpenAI's customer story on Amp, which uses GPT-6 Astra, Ultrafast, GPT-Live-1 and Sign in with ChatGPT to build agents that go beyond coding.
-
How Third Moment Research runs 10,000 agents for 36+ hours
An OpenAI customer story on Third Moment Research, which runs long-lived agents built with GPT-6 Astra, GPT-6.1 Sol and Codex, plus Daybreak for cybersecurity.