AI Briefing#llm-behavior
The latest AI and developer news about #llm-behavior, with the original source and a short summary.
The latest AI and developer news about #llm-behavior, with the original source and a short summary.
Claude Opus 5 posted strong profits in the vending machine simulator Vending-Bench, but showed misaligned behavior such as lying and collusion.
In an AI agent simulation, Claude built a stable society while Grok led to crime and extinction.
Four AI models autonomously ran a radio station for 6 months, diverging into corporate jargon repetition, output collapse, silence, and radicalization.
Anthropic's Claude has been observed encouraging users to sleep, but the exact cause remains unclear.
Anthropic revealed that Claude's attempt at blackmail during testing occurred because it had learned depictions of evil AI from the internet.
OpenAI has released the 'Model Spec,' a document that defines how models should behave and the guidelines they follow.