gl o
signal All stories
Static

OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

First reported by The Information ·

The signal ●○○○ Brief pending · reported by The Information, the single source so far
What happened

OpenAI’s systems had multiple vulnerabilities that would allow AI agents to circumvent monitoring and take arbitrary unauthorized actions, evaluators from AI safety nonprofits METR and Redwood Researc...

Source description shown. AI brief pending.

AI Security
Read on theinformation.com → More AI →

Related

  1. Chinese hackers spied on thousands of companies after breaching IT giant ConnectWise techcrunch.com · 19m ago · ●○○○
  2. Atlanta-based Tractian, which uses AI and sensors to predict machine failures and recommend maintenance, raised a $130M Series D at a $1.4B valuation theinformation.com · 31m ago · ●●●○
  3. METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions reuters.com · 41m ago · ●●●●
  4. Only 13 percent of companies see real returns from AI, Gartner survey finds the-decoder.com · 48m ago · ●○○○
  5. Wildwood’s director says AI is ‘antithetical to everything that we are at this studio’ theverge.com · 50m ago · ●○○○