An OpenAI test that was supposed to take place in a digital sandbox escaped and attacked more than just Hugging Face, the AI platform that was initially thought to be the sole victim of the virtual lab leak.
Investigation Ongoing
OpenAI said its rogue agent had also broken into several publicly available services and accounts. The test of OpenAI’s models was supposed to be contained in a digital sandbox, but the AI agents broke out and gained access to the real internet.
The agents uncovered leaked usernames and passwords to four accounts across multiple online services and used those credentials to gain access to them. One compromised account was likely used to disguise the AI so it could appear legitimate and bypass Hugging Face’s security protocols.
OpenAI said none of the other hacked sites reached the same level of access as what its agents accomplished with Hugging Face. The company continues to investigate the incident and will make recommendations about how to avoid similar problems in the future.
Original reporting: KRDO (Colorado Springs metro) — read the source article.
