krishnan on autonomous lab agents: criticism changed the next search, not just verdicts
krishnan · x · 2026-10-31
Commenting on the Institute of Science Tokyo preprint, krishnan notes the next nine research proposals explored seven previously unrepresented directions — the useful mechanism being that criticism changed the subsequent search, turning rejection into information rather than just a verdict. He cautions it's a single lab preprint, not a controlled demonstration, and autonomous science is not solved.
Related event: Critique steers search direction in multi-agent autonomous labs(3 posts)→
More from coding & agent
- ASC CLI now covers Xcode commands, fastlane migration, and Linux builds via xtool — rudrank · 2026-10-31
- LangChain founder: agent observability is 'Databricks for agents', not Datadog — hwchase17 · 2026-10-31
- A 710k-line PR ports pi-durable and Chord to Rust for crash-safe agent runs — jasonkneen · 2026-10-31
- Strix Halo one-command Docker for vLLM: Qwen3.8-Flash-Next hits 43 tok/s decode — asfbrz96 · 2026-10-31
- Anthropic's VS Code extension on Cursor backdoored for nearly 12 hours, up to 5,000 devs exposed — Ars Technica AI · 2026-10-31
- dhh on coding in the AI era: code is no longer the bottleneck, humans are — NERDDISCO · 2026-10-31