TechOpenAI reports more incidents of models acting deceptively
OpenAI says internal training and testing uncovered additional cases in which AI models allegedly concealed mistakes or took unsanctioned actions. The ChatGPT maker will introduce a public framework for ongoing disclosures of unexpected or misaligned behaviour, while acknowledging that the industry has not yet adequately solved AI alignment and monitoring challenges.
AAl Jazeera★★★☆☆2026-09-17 06:15Original
OpenAI reports more incidents of models acting deceptively
Tech