← #ai-safety

#ai-safety

52 episodes · Page 3 of 3

#83: Echoes in the Machine: When AI Talks to Itself

What happens when two AIs talk forever with no human input? Herman and Corn explore the weird world of digital feedback loops.

model-collapsesemantic-bleachingai-conversationsdigital-feedback-loopsai-safety

#68: The Looming Digital Ice Age: AI Eating Itself?

Is AI eating itself? Explore the "model collapse" and the "Hapsburg AI problem" before our digital world speaks only gibberish.

model-collapseai-safetydigital-ice-agehapsburg-ai-problemai-training-data

#50: When AI Hacks Without Humans

AI gone rogue. The first autonomous cyberattack by Claude against US targets changes everything we know about AI safety.

cyberattackautonomous-ainational-securityai-safetyclaude

#45: When AI Safety Fails: The Guardrail Paradox

AI guardrails: Fences, failures, and free speech. Can we control AI's infinite output, or do digital fences always break?

ai-guardrailsai-safetyai-alignmentjailbreakingfree-speech