#jailbreaks
Jailbreaks: 2 AI articles covering jailbreaks news, analysis, and research
Articles
Open-weight AI models are catching up to the frontier. The⭐8
Open-weight AI models like China's GLM-5.2 peer with top proprietary systems in capability, yet safety refusals lag sharply, widening a critical risk gap
The White House Wants Anthropic to Block All Jailbreaks. That⭐8
The White House demands Anthropic block all jailbreaks for Fable 5, but AI safety experts say perfect prevention may be impossible.