Ch(e)at GPT? - Computerphile

Name: Ch(e)at GPT? - Computerphile
Description: Computerphile video in which Mike Pound explains a University of Maryland paper on watermarking LLM output. The method biases token choices so generated text can later be detected statistically.

Computerphile

Computerphile video in which Mike Pound explains a University of Maryland paper on watermarking LLM output. The method biases token choices so generated text can later be detected statistically.

Linked as the approachable explanation whenever HN discusses detecting or watermarking AI-generated text.

6 Hacker News mentions · 2023–2026

Topics

LLMs & generative AI
Cryptography

Watch on YouTube

Explore more videos