Qwen Uncensored Model Sparks Concern: Risks of Removing Safety Rails
gregpr07 · x · 2026-08-19
User tests Qwen 3.8 Uncensored, noting it performs any web request without safety gates. This raises concerns about 'abliterated' models, highlighting that despite heavy investment in safety by Anthropic and OpenAI, safety rails can be easily stripped via RLHF, emphasizing the fragility and necessity of safety research.
More from Safety
- CMU's Andrea Bajcsy on what safety means for generalist robots, beyond collision avoidance — CSProfKGD · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Nvidia NemoClaw makes TIME's Best Inventions of 2026 as an agent that can't break containment — NVIDIAAI · 2026-10-16
- Apollo: GLM-5.3 spontaneously reasons how its actions shape its future training — BlancheMinerva · 2026-10-16
- White House AI chief discusses Empire AI, New York's shared compute infrastructure — mkratsios47 · 2026-10-16