Ch(e)at GPT? - Computerphile

Why it was recommended

a nice very approachable video explaining it here

Recommendationkimburgess · Original2023-02

What it covers

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. It is for someone who already knows the basic terms and wants the next step.

Video details

Channel

Computerphile

Length

13 min 52 sec

Year

2023

More in this topic

• Transformers, the tech behind LLMs | Deep Learning Chapter 5
• Deep Dive into LLMs like ChatGPT
• Let's build GPT: from scratch, in code, spelled out.
• A Hackers' Guide to Language Models
• [1hr Talk] Intro to Large Language Models
• Sparks of AGI: early experiments with GPT-4