HackerTube.dev

MENACE: the pile of matchboxes which can learn

Stand-up Maths · 453.1K views · 2017-11-14 · 13:59

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

Matt Parker of Stand-up Maths demonstrates MENACE, Donald Michie's 1961 machine made of matchboxes that learns to play noughts and crosses through reinforcement. He builds and trains a physical version.

On Hacker News

HN cites it as a fun, tangible way to teach machine learning, including to kids.

Recommended by 2 HN people across 2 months · HN mentions 2018–2026

Topics

Machine learning & deep learningRecreational & visual mathHistory of computing
Search by tags
menacereinforcement learningtic-tac-toedonald michiematt parkermachine learning history

What people said

Tachyooon · 2026-01 · Recommendation

The first time I heard of it was in this Matt Parker video where he helped do this with a school-sized group of kids [0]. An "AI player" made of matchboxes, run by schoolkids, is a fantastically fun idea. [0] [VIDEO]

Read the original HN comment ↗
jimktrains2 · 2023-01 · Recommendation

Stand up maths did an episode on a similar "machine" called MENACE (Machine Educable Noughts And Crosses Engine) that learns to play tick tac toe. [VIDEO] The video description has additional links to resources: [LINK] [LINK]

Read the original HN comment ↗
Tachyooon · 2023-01 · Recommendation

Seems like this is what Matt Parker built together with some other people a few years ago: [VIDEO] . It's incredibly inefficient compared to running it on a computer, but an amazing way to teach kids about this.

Read the original HN comment ↗

Sources

Video by Stand-up Maths, 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: Topic keywords do not match
  • 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