For $20, a Coding Agent Devises a Surprising Physical Strategy to Move a Box
tomssilver · x · 2026-10-21
Given the instruction "put the green box on target, clearing obstructions," the agent Astra generated a purely Python solution in a red-teamed sandbox with no other tools and a $20 budget — using a surprising physical strategy. Princeton's Tom Silver says he's adding it to his catalogue of surprising physical strategies discovered by coding agents.
More from coding & agent
- A daily 3am AI loop that audits your last 24 hours of dev work — mariofilhoml · 2026-10-21
- Surge AI's sudo L7: 60 real-repo tasks testing if coding agents act like staff engineers — echen · 2026-10-21
- sudo L7 benchmark: Claude Opus 5.5 matches GPT-6.1 on code, leads 23 points on judgment — echen · 2026-10-21
- Legacy software's biggest risk isn't AI, it's the inability to ship — matt_slotnick · 2026-10-21
- Letting Codex run a 300k-LOC app for a year spawned 535 copies of index.md — AggressiveCoast190 · 2026-10-21
- A simple context hygiene trick for Claude Code: audit CLAUDE.md with claude-md-management — daniel_mac8 · 2026-10-21