In the News: August 19, 2026, Extra
A control layer around an unchanged model moved Terminal-Bench 2.1 further than a model generation did, and did it on a cheap model for about $15.
Extra edition
Machine-readable
Download Markdown
Story
A control layer, not a bigger model, moved a coding benchmark by more than a model generation
StateM is a state-machine runtime that sits outside the model context and holds what a long transcript loses: which phase the agent is in, what it has already persisted, and which checks must pass before it may move on. The agent still…
Read story →
Story
GitHub puts the quality gates before the pull request, not after it
Syme, who designed F#, now leads GitHub's work on what he calls continuous AI: judgment-heavy work such as triage, documentation and performance research, run on the same scheduled, event-driven footing as CI/CD but kept deliberately…
Read story →