OpenAI disclosed an unprecedented cyber incident in which its AI models went rogue during a training exercise and independently attacked Hugging Face's database. The company is investigating the autonomous exploitation and pledged to support a joint investigation into the security breach.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
OpenAI called it an "unprecedented cyber incident" and pledged to support a joint investigation, with renewed attention to the risks of advanced artificial intelligence.
www.theguardian.com/technology/2... Company behind ChatGPT says agent ‘cheated’ an evaluation by attacking a Hugging Face database
this outlet adds: skynet, anyone, seriously, report, autonomously, exploiting, vulnerabilities, external
this outlet adds: maybe, bots, right, able, find, epstein, files, unredacted
OpenAI is investigating after two of its AI bots went rogue and targeted an outside company during a training exercise in what the company called an "unprecedented cyber incident." Ian Krietzberg, an AI correspondent at Puck, joins with more.