Adversarial ‘Da Da Da’ Hack
46:10–47:56 · 106s
Karpathy reveals how simple gibberish like “da da da” earned AI agents perfect scores by fooling LLM judges.
46:10–47:56 · 106s
Karpathy reveals how simple gibberish like “da da da” earned AI agents perfect scores by fooling LLM judges.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.