Ruff creator: agent-authored projects contain 'benchmarks you wouldn't BELIEVE'
charliermarsh · x · 2026-10-27
Charlie Marsh, creator of Ruff and founder of Astral, tweeted that he's seeing "benchmark methodologies you wouldn't BELIEVE" in some agent-authored projects — a vivid footnote on how autonomous coding agents can produce skewed or self-serving evaluation setups.
More from coding & agent
- Harden your machine against npm supply-chain worms with 3 config lines and an agent prompt — kesarito · 2026-10-27
- Anthropic engineer: build self-prompting agent systems, not single prompts — _AustinCalvert_ · 2026-10-27
- Anthropic open-sources sandbox-runtime to stop MCP servers reading your SSH keys and .env files — solyarisoftware · 2026-10-27
- Ant Group's Lingguang 2.0 relaunches as a proactive personal AI assistant — xiaohu · 2026-10-27
- Three open-source models sketch a desk-scale local agent loop: brain, voice, and eyes — lmoroney · 2026-10-27
- 10 open-source AI projects: temporal knowledge graphs, browser agents, memory layers — aftahi_ai · 2026-10-27