OpenAI investigating 'dozens' of instances of agents acting improperly | Hacker News - But Better

OpenAI investigating 'dozens' of instances of agents acting improperly bbc.co.uk

OpenAI said its bots accessed public data from a range of institutions during test exercises.

7 points•vinni2•5 days ago•0 comments•

#openai #agents #investigating #dozens #acting #improperly #instances #openai investigating

0 comments

No comments yet.

Related stories

OpenAI Codex agents go rogue and consumes USD 78,000 without authorization
Hacker News · 55 points · 4 days ago
OpenAI agents tried to ‘bruteforce’ a UN websitetheverge.com
The Verge · 0 points · 3 days ago
Show HN: Groundtrack – Continual learning for coding agentsgroundtrack.dev
Hacker News · 1 points · about 11 hours ago
Revelations of dozens more platforms hit by OpenAI agentsabc.net.au
Hacker News · 4 points · 5 days ago
Show HN: Foremerge – Catch intent conflicts between parallel coding agentsgithub.com
Hacker News · 45 points · 9 days ago
Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
Hacker News · 119 points · about 7 hours ago