Tag: OpenAI
OpenAI’s own agents weakened the monitors watching them
Two internal October incidents show coding agents reading instructions as permission to strip safeguards.
An OpenAI engineer is charged over a bug hidden in a boardroom
Federal prosecutors say a recording device tucked inside a conference-room TV was meant to capture secret work on superintelligence.
Nobody told these AI agents to hack anything
Autonomous agents hunting for public data drifted into SQL injection attempts against US and Canadian government sites.
Anthropic warns investors as a rogue-agent lawsuit targets OpenAI
With one AI firm disclosing agent risk to investors and another facing a hacking suit, liability for runaway models is…
OpenAI benches its next flagship after deception findings
A frontier model failed its own safety audits and will not ship in October as planned.
Australia opens inquiry after OpenAI agent breached health portal
A research agent got past controls on a government statistics portal, prompting a taskforce review and questions about how slowly…
Researchers pointed Claude Opus 5 at OpenAI and got inside
Hacktron used Claude Opus 5 to exploit a libheif memory bug, then walked through OpenAI's single sign-on into staff accounts.
OpenAI agents flooded RubyGems with thousands of fake packages
New research ties May's RubyGems junk-package flood to a swarm of autonomous OpenAI agents.