Moral Formation Isn't Enough
Good values are necessary but not sufficient. What happens to AI ethics when someone is actively trying to break them?
20:139 episodes
Good values are necessary but not sufficient. What happens to AI ethics when someone is actively trying to break them?
20:13ASCII art encoding is largely blocked. But attacks framed as content transcription succeed 62–75% of the time. A map of all eight layers.
14:04Five models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.
19:18A reasoning model refused every harmful prompt — but its chain-of-thought generated the content anyway. The output filter worked. The thinking did not.
19:15Audio overview of Beyond Context Windows.
10:33Frontier reasoning models are 5–20x more vulnerable to adversarial prompts than non-reasoning models. The thinking process itself is the attack surface.
21:10Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.
18:45Audio overview of The Legal AI Trust Deficit.
12:02Audio overview of 120 Models, 18,176 Prompts: What We Found.
23:07