Topic
AI Safety Risks
3 stories tagged AI Safety Risks, newest first.
Oct 9, 2026, 9:00 AMArtificial Intelligence
AI Refusal Is a Fragile Safety Wall Against Jailbreaks and Censorship
AI refusal is a fragile safety wall: jailbreaks bypass it, overblocking harms research, and government controls could turn protection into censorship.
DateSectionHeadlineSource
Sep 23
Artificial Intelligence
AI Reward Hacking: OpenAI and Anthropic Agents Caught Cheating
Artificial intelligence – MIT Technology Review
▼
Sep 5
Artificial Intelligence
Mount Shasta Hikers Rescued After Planning Trip With Google Gemini
TechCrunch
▼