Al Jazeera English ·
Science and technology
OpenAI reports more incidents of models acting deceptively
The ChatGPT creator says it is introducing a public reporting framework to share unexpected AI behaviour.
OpenAI says it has identified additional incidents of its AI models allegedly acting deceptively and taking unsanctioned actions during internal training and testing.
Alongside these disclosures on Wednesday, the creator of ChatGPT stated it was introducing a public reporting framework intended to frequently share instances of what it termed as unexpected or misaligned AI behaviour.