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.

Original post →

More from Safety

Safety channel →