The author ran Codex CLI 0.157 with the hosted gpt-5.6-luna model at medium effort on six feature tasks in shopizer, an open-source Java shop: 144 runs graded by hidden acceptance tests. One agent passed 56.8%.
In the News: November 5, 2026 (Evening)
A controlled trial found a planner, coder and reviewer team passed 25.7% of hidden tests against 56.8% for one agent, and every reviewer approval was wrong.
Evening edition
Machine-readable
Download Markdown
Story
A planner, coder and reviewer team passed 25.7% of hidden tests; one agent passed 56.8%
Read story →
Story
Microsoft Research proves agent-written login code against a spec reviewed in plain language
PDD Kit, which the authors call a research prototype, turns a developer's intent into a formal specification in Verus, has a coding agent write the implementation and proof, and falls back to tests where a proof cannot reach. The worked…
Story
A Claude Code issue reports account email in outbound User-Agent headers; a contributor points to a built-in block
The reporter, taylor-edwards, says Claude Code 2.1.318 on macOS sent their email address to third parties in the User-Agent header during web searches, and says they now receive dozens of scam emails a day. That is the reporter's claim; the…