Clauday.

If harness design decides how well an agent does, the next step is obvious: let agents design the harness. MILO (arXiv 2609.38349) does this, and it beats every hand-built harness …

Terminal agents have a problem that chat models do not: a bad action changes the world. Install the wrong package and every later step works in a broken environment, even if the mo…

Let an agent write its own homework and grade it too, and eventually the proposer and the grader learn to make the same mistakes. "False Frontiers" (arXiv 2609.39102, 180 upvotes o…

Photon held an actual funeral for mobile apps: in a San Francisco church on September 17, with speeches and a coffin for app icons. Two weeks later it has the money to back the jok…

Restate was not built for agents. It just turned out to be exactly what agents need. The Berlin startup raised a $20 million Series A led by Singular, with Redpoint Ventures and Ca…

Most coding agents add features every week. Pi waited months to add five. Earendil shipped Pi 1.0 on October 1 and it hit 451 points on Hacker News. Pi already has hundreds of thou…

Google's most capable model is out, and almost nobody can use it. Gemini 4 Argon launched on September 30, but it is going only to trusted cyber defenders in Google's Fairwind Prog…

A month ago "decision model" was one startup's pitch. This week it became a product category. OpenAI announced a Decisions API at Dev Day on Tuesday. On Thursday, Cloudflare releas…

Every skill scanner on the market checks skills one at a time. Skill cascading attacks are built to pass exactly that test. The paper, from Zihao Zhu, Siwei Lyu, Adel Bibi and Baoy…

Offensive-security benchmarks are saturating, and ScopeBench argues they were measuring the wrong thing anyway. In a real penetration test the question is not whether an agent can …