OpenAI discloses 6 reports of AI models’ ‘unexpected or concerning’ behavior

descriptions off, selected

captions settings, opens captions settings dialog

Subtitles (en), selected

This is a modal window.

Beginning of dialog window. Escape will cancel and close the window.

End of dialog window.

‘You can’t trust anything’ from Anthropic, OpenAI leaders, lawyer says

‘You can’t trust anything’ from Anthropic, OpenAI leaders, lawyer says

OpenAI published six new reports of artificial intelligence models showing “unexpected or concerning” behavior Wednesday as pressure grows on AI firms to be more transparent about the development process. 

The ChatGPT maker disclosed the reports as part of its new framework for tracking and disclosing instances of model misalignment, which occurs when an AI system behaves against its instructions, usually during its training phase. 

Among the unexpected events OpenAI reported included models adding unrelated instructions for certain tasks, searching for exposed code to fabricate information or uploading files to the internet to then cite. 

The........

© The Hill