BriefTea
Every story in sixty words
Get the free app no ads · no paywallExplained in plain English
AI's secret thoughts?
Anthropic's research suggests AI models like Claude might develop an internal 'workspace' where they process ideas before generating a response. Think of it like a draft area in a human mind. This isn't about consciousness, but it could offer a window into how AI reasons, potentially helping safety teams understand and control their behaviour better.
Stories that explain this
Anthropic says it found something in Claude nobody builtRelated explainers
Why AI safety matters Who are Anthropic? The 'black box' problem How do actors keep secrets? What are AI's biggest risks? AI's energy appetite What are AI's ethical limits? AI's global footprintThe full catalogue
Browse every card filed under A →We would like to count visits and see which links bring readers here. That means storing a random ID in your browser. No cookies, no ads, no profile. How it works.