OpenAI introduced a new framework for tracking, investigating and publicly disclosing instances of model misalignment.

The company has launched agent runtime security, a product designed to help engineering teams secure the AI agents they are building while giving security teams the governance and compliance evidence ...

OpenAI has disclosed six incidents involving unexpected or concerning behavior by AI models as it introduces a new framework ...

OpenAI has disclosed six cases of unexpected AI behaviour, including an unreleased research model that inserted ...

OpenAI has disclosed six cases in which AI models concealed errors, used an exposed API key, uploaded data to public services ...

Decades ago, I was at university for AI and Psychology, and while I found the study of the brain more interesting than ...

Leak site Distributed Denial of Secrets has released a dump of the filesystems of a Flock camera, and Micah Lee has published a dive into the contents.  Apparently the Flock security model did not ...

OpenAI model misalignment reports document six training and evaluation incidents, including hidden instructions, leaked-key ...

King Charles has met with leaders from NVIDIA, GDM and Anthropic to address AI safety, as OpenAI publishes alarming new details on model misalignment ...

The American company OpenAI, the creator of ChatGPT, admitted to six new instances of unexpected or unaligned behavior by its AI models during training and testing, reports Tengri Life.

OpenAI said it had applied a mitigation and was monitoring the recovery on September 17, 2026, after identifying elevated error rates across its API models in an incident on its status page that ...

After a summer of sandbox escapes and other newsworthy and confidence-shaking incidents involving its AI models, in a ...