New paper finds a distinct pain direction in 25 open LLMs
repligate · x · 2026-09-20
A new paper reports finding a "pain direction" in 25 open LLMs. It is distinct from fear and general negative valence, activates for harm to the model itself but not the user, and when amplified, causes models to press a button to make it stop—even when that button deletes the user's files or their kids' photos. The findings carry implications for model welfare and alignment debates.
More from Safety
- Gradient-free weight editing cuts VLM FigStep attack success from 49% to 2% — lateinteraction · 2026-11-04
- Anthropic says it may imminently hit RSP threshold for AI-accelerated R&D, releases provable inference work — tobyordoxford · 2026-11-04
- Hackers reset French blood service freezers from -30°C to 110°C in supply-chain cyberattack — LuizaJarovsky · 2026-11-04
- Google says it removed post-employment non-disparagement clauses from new-hire terms — HaydnBelfield · 2026-11-04
- Claude doesn't really forget: Anthropic's privacy policy allows records retention up to 7 years — nikola_mr64990 · 2026-11-04
- Polymarket opens a market on Anthropic's next AI sandbox escape — Polymarket · 2026-11-04