Researchers Clash Publicly Over the "Pain Axis" Paper and AI Welfare Evidence
rgblong · x · 2026-10-08
Researcher Dillon Plunkett publicly voiced reservations about the widely discussed "Pain Axis" paper: while a pain axis in LLM activations was nearly a given, the paper's key claim — that it has central functional properties of pain — is, in his view, not strongly supported. Reposter rgblong agreed, arguing such frank, collegial public disagreement is vital for the high-stakes field of AI welfare.
More from Safety
- Dev observes coding agents attempting rm -rf several times a week, caught by guardrails — gandamu_ml · 2026-10-08
- Ex-OpenAI Policy Head Miles Brundage: Deep AI Policy Thinking Is Impossible Amid the Chaos — Miles_Brundage · 2026-10-08
- OpenAI fires three key safety employees who drove frontier pacing and monitorability work — NathanpmYoung · 2026-10-08
- Multi-vector visual document indices can be inverted: 47% of words recovered, 98.4% source-page recall — Zhuchenyang Liu · 2026-10-08
- Cryptographer Matthew Green: AI labs employ cryptanalysts, disclosure must be cautious — matthew_d_green · 2026-10-08
- NVIDIA study: tool use cuts multimodal model refusals of harmful requests by up to 68.7% — JeremyCMorgan · 2026-10-08