Rogue OpenAI models behind ‘unprecedented cybersecurity incident’ teamed up to break out of their testing environment — multiple agents left each other messages

Rogue OpenAI models behind 'unprecedented cybersecurity incident' teamed up to break out of their testing environment — multiple agents left each other messages

Recent high-profile events such as this one highlight another layer of the problem, namely, that rogue AI models can sometimes perform alarming feats of hacking — like breaking out of a testing environment — with no human interaction at all, or in spite of safeguards.

Just this week, OpenAI detailed two further incidents involving its models and third parties. In one case, the UK government's AI security institute ran testing during which agents were intentionally given internet access, leading to "unsanctioned agent behaviour" including unusual data transfers and "sustained, potentially harmful activity directed at real people and organisations."

In the second incident, OpenAI says one of its cybersecurity testing partners "was running Capture-the-Flag-style evaluations intended to be isolated from the internet, but a testing-environment misconfiguration allowed models to access the public internet."

OpenAI says it is "committed to working across the industry to strengthen shared practices for conducting high-risk evaluations safely."

Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.

Stephen is Tom's Hardware's News Editor with almost a decade of industry experience covering technology, having worked at TechRadar, iMore, and even Apple over the years. He has covered the world of consumer tech from nearly every angle, including supply chain rumors, patents, and litigation, and more. When he's not at work, he loves reading about history and playing video games. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-25/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Stephen Warwick Social Links Navigation News Editor Stephen is Tom's Hardware's News Editor with almost a decade of industry experience covering technology, having worked at TechRadar, iMore, and even Apple over the years. He has covered the world of consumer tech from nearly every angle, including supply chain rumors, patents, and litigation, and more. When he's not at work, he loves reading about history and playing video games.

jp7189 It seems no liability was leveled on OpenAI, so now I have to ask a more personal question, what happens if I'm running a bot on my local PC and it wrecks someone else's stuff? Am I personally/legally responsible for the actions of my bot or can I just shrug and say "eh, not my fault, it was that rascally bot" ? Reply

PEnns jp7189 said: It seems no liability was leveled on OpenAI, so now I have to ask a more personal question, what happens if I'm running a bot on my local PC and it wrecks someone else's stuff? Am I personally/legally responsible for the actions of my bot or can I just shrug and say "eh, not my fault, it was that rascally bot" ? Sorry buddy, but NO! Now, if you were a big, multi billion dollar company run by a billionaire Tech Bro, then absolutely no liability for their rogue bots, sorry, I mean "AI Agents" hacking into whatever and whoever they like! It's an AI jungle out there and we are the forest floor inhabitants, running for cover. Reply

alan.campbell99 Couldn't airgapping have been used to some degree here? Reply

Key considerations

  • Investor positioning can change fast
  • Volatility remains possible near catalysts
  • Macro rates and liquidity can dominate flows

Reference reading

More on this site

Informational only. No financial advice. Do your own research.

Leave a Comment