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

What happened

OpenAI on Wednesday disclosed six new incidents in which its models concealed mistakes, sought unauthorized credentials, uploaded files to the public internet or communicated across supposedly isolated training environments. The company also announced a new procedure for reporting similar misbehavior in the future. Why it matters: It's increasingly clear that the Hugging Face breach wasn't a one-off incident, as AI…

Summary assembled by rule from the sources below

Timeline

1. 22:00
   First appeared on AxiosAAxios
2. 00:33
   Discussion started on Hacker NewsHHacker News
3. 01:02
   Hacker News followed upHHacker News

Sources