Frontier models refuse more genomics requests as reasoning effort rises, Carbon-X team finds
LoubnaBenAllal1 · x · 2026-10-22
The Carbon-X team highlights why open science matters in AI for biology: frontier models often refuse routine genomics requests. On next-base prediction, Opus 5.5 drops from 17.7% at low reasoning effort to 1.1% at max effort as its refusal rate climbs, and Gemini 4 Argon shows the same pattern (31% → 8%), hindering legitimate research.
More from Safety
- Survey of 106,000+ US public servants reveals how government actually uses AI — mchorowitz · 2026-10-22
- OpenAI reportedly runs agent swarms to hack systems and find exploits for patching — bindureddy · 2026-10-22
- Some US banks are detecting unauthorized AI agents in customer accounts — menhguin · 2026-10-22
- 60% of chatbot responses miss critical safety warnings — what does that mean for autonomous agents? — fortiplus84 · 2026-10-22
- Anthropic safety guardrails block LLM-driven crypto trading agent, dev reports — devanshmehta · 2026-10-22
- Railway breach timeline: crypto theft began 2 hours before users were told to rotate keys — banteg · 2026-10-22