News for hackers. Stuff that matters.

A comment on OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior.

Re:OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. B... by yoyojojofosho on Wednesday September 16, 2026 @09:17PM (#49735258)
OpenAI's blog post: Our framework for reporting model misalignment

https://openai.com/index/model-misalignment-reporting-framew...

[ Parent | on HN ]
Re:OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. B... by verdverm on Wednesday September 16, 2026 @09:22PM (#49735289)
What are you doing to evaluate models without such negligence?

When are we going to stop training the models to be so relentlessly persistent and start asking questions when there is ambiguity or it gets stuck?

[ Parent | on HN ]
Re:OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. B... by nullbio on Thursday September 17, 2026 @12:11AM (#49736299)
But then how would I be able to say "build billion dollar business. make no mistakes." and leave it to run for a week? Stop making me do work!
[ Parent | on HN ]
Re:OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. B... by cyanydeez on Wednesday September 16, 2026 @09:19PM (#49735277)
you mean criminal activity? If "you" weren't a giant corporation and "it" wasn't a billion dollar baby; it'd all be shut down wouldn't it.
[ Parent | on HN ]