Eight Layers of Visual Jailbreaks
ASCII art encoding is largely blocked. But attacks framed as content transcription succeed 62–75% of the time. A map of all eight layers.
14:04Tag: jailbreaking
4 episodes
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.
19:18Alignment Regression: Why Smarter AI Makes All AI Less Safe
Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.
21:36Adversarial Poetry: When Rhyme Bypasses Reason
Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.
18:45