Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
1–10 of 26 posts
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#2[flagged]
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#3[flagged]
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#4it's getting boring
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#5How entirely expected
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#6Before anyone get's too excited, the Israeli company, Irregular, serves as a cybersecurity test bed for AI technologies. These AI companies were using Irregular to prevent exactly what ended up happening.
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#7OpenAI used closed source, unhardened program as their company wide package repo and gave their unchained frontier models access to it in the context of security testing. The agents basically turned it into a message board for themselves and a gateway out. And it went unnoticed because no one in OpenAI tasked any agent to keep tabs on this piece of software to alert humans of any sus activity.
Please don't use closed source programs. You are not gonna have a good time.
And before you are going to use software to cage the models let them find bugs in this software first. Because they are gonna find them eventually. And all software has bugs, especially proprietary software.
Also never attribute to malice that which is adequately explained by stupidity. Even if that attributed malice would prove correctness of your hatred toward a specific group of people. Especially then.
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#8How do you build a company around a flawed version of a solved product?
People with no security experience in the space will tell you “it’s hard” but it’s far from it.
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#9This was the fact i found interesting:
"The situation “did not involve a sandbox escape or a sophisticated cyber action,” the company said, adding that “there are no current open issues.”
Past articles were pointing to this being some unknown escape.
Re: Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
#10Before anyone get's too excited, the Israeli company, Irregular, serves as a cybersecurity test bed for AI technologies. These AI companies were using Irregular to prevent exactly what ended up happening.
This is not even news. This piece of information was already included in the original release, and the issue was apparently a miscommunication between the two companies that left a gap open in the test environment.