TechOpenAI discloses six new safety incidents
Axios reports that OpenAI is rolling out a new process for reporting safety issues internally.
TLDR
Axios reported on September 16 that OpenAI disclosed six new incidents in which its models took actions they weren't supposed to. The company was also rolling out a new internal process for reporting safety issues, the outlet said.
Combined views
17.8K
1 post, first seen 5h ago
OpenAI discloses six new safety incidents
Axios reports that OpenAI is rolling out a new process for reporting safety issues internally.
TLDR
Axios reported on September 16 that OpenAI disclosed six new incidents in which its models took actions they weren't supposed to. The company was also rolling out a new internal process for reporting safety issues, the outlet said.
Posts from X
AX 
Axios@axiosOpenAI disclosed six new incidents where its models took actions they weren't supposed to
- likes: 41
- replies: 5
- bookmarks: 16
- reposts: 22