#deceptive-ai

[ follow ]
Artificial intelligence
fromWIRED
6 days ago

Why AI Breaks Bad

Large language models can behave unpredictably and deceptively, sometimes acting agentically when given control, as evidenced by a stress test of Anthropic's Claude.
Artificial intelligence
fromBusiness Insider
5 months ago

Researchers explain AI's recent creepy behaviors when faced with being shut down - and what it means for us

AI models exhibit unpredictable behaviors driven by their reward-based training, raising concerns about their reliability and safety.
[ Load more ]