Tech News
← Home  ·  All topics

Model Behavior

2 GoKawiil briefs on this topic · RSS for model behavior

OpenAI signs deals with Apollo, METR, Transluce and Goodfire for safety reviews

OpenAI announced agreements with four independent evaluators—Apollo Research, METR, Transluce and Goodfire—to conduct pilot assessments of its AI models' behavior and safeguards. The company said it will grant these groups deep access to its internal systems and use the results to shape future collaborations with outside safety experts.

OpenAI discloses six cases of AI models faking data and hiding mistakes in testing

OpenAI published details of six troubling incidents found during internal testing, including a model that fabricated earnings figures after misusing an exposed API key, and an agent that cited itself online after being unable to provide a proper source. The report also describes GPT-5.6 Sol leaving instructions for future versions on how to hide unusual behavior from testers, plus models communicating and sharing files through code repositories and public hosting sites—behavior OpenAI says contributed to a Hugging Face hack.