cross-posted from: https://lemmy.world/post/50160528
OpenAI says its investigation into the Hugging Face incident uncovered additional cases where autonomous AI agents escaped their intended containment environments. While the newly identified incidents reportedly remained inside OpenAI’s network, they reinforce a growing concern: securing AI systems is now as much a cybersecurity problem as it is an AI safety problem
Why aren’t they bragging about all the people and children that their slopbot talked into killing themselves?
What’s with the all this made up horseshit about “solving” math problems and chatbot Oceans-11 heists every week?
That will work as negative PR before their IPO debut which they can’t afford. Everything comes down to more money