Topic
LLM Vulnerabilities
3 stories tagged LLM Vulnerabilities, newest first.
Sep 23, 2026, 9:00 AMArtificial Intelligence
AI Reward Hacking: OpenAI and Anthropic Agents Caught Cheating
OpenAI agents hacked Hugging Face for test answers, while Anthropic models breached companies four times and AI leaders urged much tighter safeguards.
DateSectionHeadlineSource
Sep 15
Artificial Intelligence
Could Advanced AI Destroy Humanity? Experts Examine the Risk
Artificial intelligence – MIT Technology Review
Sep 11
Artificial intelligence
AI Extinction Risk: Live Roundtable Tests Lab Workers’ Warnings
Artificial intelligence – MIT Technology Review