The AI security leaderboard finds that Frontier models like Claude (Fable 5) and GPT-5.6 Soul withstand all tested attacks, but hundreds of universal jailbreaks exist in Gemini 3.1 Pro and Grok 4.5 at very low cost.

5:00how to use AI models and jailbreak them. So uh you know that that's kind of I think a sign of what's to to come and all Frontier developers do have some safeguards in their models to try and prevent both misuse and this kind of loss of control, but there's just never been a systematic evaluation of those safeguards. So what we did in this report was we compiled both publicly

5:24available gel breaks and and some methods of our own devising. And it it was actually pretty simple. We just tested random combinations of these as well as some expert guided combinations where we put the probability mass morum methods we thought were likely to work and then pitted around 1,500 of those against the four frontier proprietary models. And kind of the good news is that we actually found that Fable 5 and

5:49GPD 5.6 Soul withtood all of these attacks, but we found hundreds of universal jailbreaks in Gro 4.5 and Gemini 3.1 Pro and actually for a pretty low cost. So this was less than $300 in API credits to find one of these jailbreaks. So well within the resources of most attackers and certainly kind of nation states that might be seeking to abuse these models. >> As a lifelong Detroiter, it pains me to

6:18say that Boka Haram is ahead of the big three when it comes to AI adoption. I didn't think I'd ever utter that sentence. I don't know if you have a sociological take on how in the world that's happening, but it's a real puzzle from my perspective. Yeah, I I mean I I think that it's it's only interesting to see just how different organizations adopt these models and so like you know everyone's