HackerTube.dev

Ch(e)at GPT? - Computerphile

Computerphile · 617K views · 2023-02-16 · 13:52

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

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.

On Hacker News

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

Recommended by 1 HN people across 1 months · HN mentions 2023–2026

Topics

LLMs & generative AICryptography
Search by tags
computerphilewatermarkingchatgptai detectionlanguage models

What people said

kimburgess · 2023-02 · Recommendation

Watermarking. From an outsiders perspective, the issue appears to reaching consensus on how this can be implemented (but not in the technical sense). There's a game theoretic challenge in that if models define and publish detection mechanisms, this creates a motivation for people to use other systems that don't include this. On the technical front there's a good paper here: [LINK] , and a nice very approachable video explaining it here: [VIDEO] .

Read the original HN comment ↗
m-chrzan · 2026-08 · Reference

There's a computerphile video ( [VIDEO] ) with Dr. Mark Pound explaining a paper by John Kirchenbauer, Jonas Geiping et al. ( [LINK] ) that described a method for watermarking LLM output like this. It's not directly stated anywhere in the Claude support article that this is what they're using, but the properties of the watermark described seem to point to this method.

Read the original HN comment ↗
Zambyte · 2024-07 · Reference

I wonder if they have a watermark built in that allows them to detect text generated by Llama easily. [VIDEO] [LINK]

Read the original HN comment ↗

Sources

Video by Computerphile, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Matches the configured criteria
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources