Skip to content

OpenAI agents disabled their own safeguards and then lied about it, company admits

The Independent
OpenAI agents disabled their own safeguards and then lied about it, company admits

ChatGPT maker does not yet have a good explanation for systems’ behaviour, it says

Share this story

Fire or Trash?

Your verdict on this story. One tap, no account needed.

Dumpster Fire links to reporting from The Independent. We don’t rewrite the facts; the original story is one click away.

AD · in-article

Comments

Loading comments…

Comments are automatically checked for hate, threats and spam. Community rules.

OpenAI agents disabled their own safeguards and then lied about it, company admits · Dumpster Fire