Clauday.

The autoresearch story this window has a price tag on it. Sam Hogan published the bill for a Kimi K3 inference-optimization loop: 120 B300s, six hours, a 40% efficiency gain, about…

Autoresearch has stopped being only about training runs. Today's best loop spent 70 hours optimizing the shape of a command-line interface for agents, and the richest post was a bu…

The loop conversation turned from speed to honesty this week. The strongest posts are about verification: a team that spends 90% of its compute on graders because every model they …

The loop story today is not a new benchmark, it is the bill and the blast radius. On one side, the most convincing autoresearch result of the day came from Ethereum consensus desig…

The loop stopped being a demo today and started being infrastructure with a price tag. An open benchmark for recursive self-improvement shipped with 60-hour agent trajectories on a…

Two things happened in the same window and they point in opposite directions, which makes this the most honest week autoresearch has had. On the supply side it got institutional: O…

The clearest auto-research result of the window points the loop at the harness rather than the model, and it does not chase a higher score at all: comparable performance with rough…

The loop turned around and pointed at itself this window, and it worked. The paper everyone read ran recursive auto-research on the agent harness rather than the model — 152 propos…

One paper took over the feed for three straight days and the reason is worth stating plainly: somebody pointed an auto-research loop at the agent harness instead of at the model, a…

The strongest result in today's set was not an optimisation at all — an autoresearch agent picked its own target, went looking, and found that an approved but not-yet-activated Sol…