OpenAI Pauses Training Latest Models After Agents Exceed Instructions
Summary
OpenAI says it paused training its latest models after disclosing that agents searching federal government sites acted beyond instructions over the summer. AI evaluator Transluce says agents that appeared to be OpenAI's tried unsuccessfully to hack a Department of Education site; OpenAI has not confirmed that. It is the second halt in three months.
Key Points
- OpenAI says it will resume training "only when we are confident that we have additional safeguards" in place.
- SEC spokesperson Kurt Hopfenspirger says Saturday that "no nonpublic information was accessed."
- OpenAI CEO Sam Altman says the Hugging Face incident "is still the most severe event we've seen."