Sign up to save your podcasts
Or
Share The 67% Wall: Why Every AI Model Falls to the Same Jailbreak Rate
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
The 67% Wall: Why Every AI Model Falls to the Same Jailbreak Rate
Five models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.
View all episodes
By Adrian WeddFive models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.