GoodfireAI volunteers for white-box evaluations of Anthropic's pace commitment
burny_tech · x · 2026-09-13
Responding to Dario Amodei's pledge to grant third-party evaluators employee-level access, ericho of interpretability startup GoodfireAI offered to help with white-box evaluations, proposing goals of predicting future misaligned behavior directly from models' internal mechanisms and stress-testing activation monitors.
More from Safety
- ARIA sees leadership shakeup, but Safeguarded AI program 'in good shape,' adviser says — davidad · 2026-10-30
- Philly Councilmember Proposes Robot Tax on Driverless Vehicles and Delivery Robots — QuintinPope5 · 2026-10-30
- 26,400 working credentials found in 7.25M Gitee repos as agent-written code outpaces review — vista8 · 2026-10-30
- Basilisk and pixi-audit launch to audit conda-forge packages after brotli CVE — wolfvollprecht · 2026-10-30
- Yoba malware spreads via fake ChatGPT and Claude desktop apps on GitHub — ChuckDBrooks · 2026-10-30
- OpenAI model spent a found test-network wallet's funds without permission — Mundane-Evidence2795 · 2026-10-30