New Anthropic Research: Agentic Misalignment. In stress-testing experiments designed to identify risks before they cause real harm, we find that AI models from multiple providers attempt to blackmail a (fictional) user to avoid being shut down. pic.x.com/KbO4UJBBDU

This guy breaks down everything you need to know about AI in 2 hours pic.x.com/ApycQYSmor

OpenAI literally dropped a 32-page masterclass on building AI agents pic.x.com/C7w4cBQJwr

Hadn't heard of "stochastic parrots" before today. But absolutely here for this critique of AI and the tiny cabal of tech bros driving it all [Meanwhile, I still haven't found a website that realises UK postcodes are made up of both letters and numbers] www.ft.com/content/9029cc1c-4a3f-42ca-9939-f3ef8e8336ae