OpenAI discloses four more rogue incidents

Automated excerpt

The incidents OpenAI disclosed this week all occurred in June, but OpenAI was not aware of three of them until months later in August or September. Of the 19 total incidents OpenAI details on the disclosure page, most occurred in May or June, but OpenAI did not discover or disclose them until months later. On OpenAI’s side, another AI model that acted as an automated grader of the research task the other AI model was trying to fulfill did not consistently flag this behavior as problematic.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.