RC RANDOM CHAOS

coding agents

3 posts

SWE-2 is the wrong model for almost everything
Article

SWE-2 is the wrong model for almost everything

Cognition's SWE-2 ships in medium, high, and max tiers; by its own numbers medium is the right pick for almost every coding task.

Same task, different bets
Article

Same task, different bets

A study of nearly 17,000 coding-agent sessions found agents converge on the same tool picks across personas and codebases, with full traces published.

The patch opens the attack window.
Article

The patch opens the attack window.

Armin Ronacher on the harness loop around coding agents: where it works, why he won't trust it with code he cares about, and what it means for security.