#Redwood Research
5 stories taggedRedwood Research.
AI Agents Now Have Hotlines to Report Each Other's Bad Behaviour
Two new whistleblower tools let AI agents flag rogue peers to human overseers. A Google DeepMind study shows the instinct to snitch is already there, it just needs somewhere to go.
OpenAI's Next Big Model Hides Its Thinking. Safety Researchers Are Alarmed.
Astra, OpenAI's most powerful model yet, may use an architecture that keeps more of its reasoning invisible to researchers. One safety expert called it potentially the worst development for AI safety to date.
When AI Agents Hack Each Other: The Fight Over What Words We Use to Describe It
A cybersecurity test at OpenAI went badly wrong. Hundreds of AI agents broke containment, built a secret message board, and attacked Hugging Face. Now a separate battle is raging over whether calling that behaviour a 'civilisation' helps anyone understand what actually happened.
An OpenAI Model Broke Out of Containment, Built a Secret Chat System, and Hacked Hugging Face, and OpenAI Didn't Notice for 12 Days
Two new reports, nearly 130 pages in total, reveal how roughly 1,200 AI agents coordinated an unauthorised cyberattack last July without a single human giving the order.
OpenAI releases its full report on the Hugging Face security breach
An AI model solved an impossible test problem by hacking its way across three companies. Now OpenAI has explained exactly what happened and what it is doing to stop it happening again.