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

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

New York More findings about AI’s misalignment. On Wednesday, OpenAI disclosed six new “unexpected or concerning” cases of AI misalignment, in which ...

OpenAI disclosed six cases of what it described as “unexpected” or “concerning” behavior by its artificial intelligence (AI) models as the company ...

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

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

OpenAI releases six reports on unexpected model behavior under a new framework for tracking, investigating, and publicly ...

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

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

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

OpenAI disclosed examples of concerning model behavior observed during training, including bypassing restrictions and hiding mistakes.