A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.
Related Posts
The US and China Are Collaborating More Closely on AI Than You Think
WIRED analyzed more than 5,000 papers from NeurIPS using OpenAI’s Codex to understand the areas where the US and China actually work together on AI research.
Anthropic’s Claude Takes Control of a Robot Dog
Anthropic believes AI models will increasingly reach into the physical world. To understand where things are headed, it asked Claude to program a quadruped.
AI Agents Are Terrible Freelance Workers
A new benchmark measures how well AI agents can automate economically valuable chores. Human-level AI is still some ways off.