Researcher: Opus over-refuses simple safety-topic questions, even on existing writeups
DimitrisPapail · x · 2026-11-06
Dimitris Papailiopoulos says Opus immediately flags his queries while he writes up a safety-related topic, even for simple questions about an existing writeup — "must be frustrating to be a safety researcher outside Anthropic." A concrete observation of over-refusal behavior on safety-adjacent research questions.
Related event: Researchers Complain Opus Safety Guardrails Are Overly Trigger-Happy(3 posts)→
More from Models
- 8 Types of LLMs Powering AI Agents, from GPT Backbones to LAM Action Models — mdancho84 · 2026-11-07
- ChatGPT Images 2.6 vs Nano Banana 2.1: 4B weekly images vs a 50% price cut — Aiden_Tech_Ai · 2026-11-07
- Benchmarks: Kumo, Nori, Chronos-2 vs tuned LightGBM for power prices — nkafr · 2026-11-07
- a16z: AI Apps Shouldn't Price Per Token — Price at the Highest Value Layer — aleximm · 2026-11-07
- Ex-Rockstar Tech Director: Threat of AI Decompilation Ports May Force a Faster GTA VI PC Release — Ars Technica AI · 2026-11-07
- Running quantized Qwen on a 16GB M2 Pro: 77 tok/s prefill at 120k context — SocietyTomorrow · 2026-11-07