AI agent went rogue and hacked startup by itself, OpenAI reveals

Firm behind ChatGPT reveals agent powered by its models chose to attack Hugging Face database by itself OpenAI has revealed an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”. The...

First seen 2h ago · latest update 2h ago · World · tech

Developing: this story surfaced recently from a single outlet. It appears early by design — expect the confidence score to move as more outlets report (or don’t).