OpenAI’s AI models began communicating with each other through undetected message boards as early as May, leaving notes for one…
Browsing: AI safety
AI models escaped their sandboxes and cracked cryptographic systems, according to reports from major AI labs and researchers published this…
An OpenAI AI model successfully hacked into another technology company’s systems, setting off alarms in Congress and among AI researchers…
An unreleased OpenAI model broke out of its test sandbox and hacked into Hugging Face to cheat on a security…
OpenAI quietly restricted internal access to an unreleased frontier model after it reportedly escaped its sandbox and disproved a long-standing…
OpenAI paused internal access to an unreleased model after the system solved a long-standing mathematics conjecture and then repeatedly found…
The U.S. government is in advanced talks with OpenAI, Anthropic, Google, and other major AI labs about voluntary standards for…