✳flâneur — a map of the web's best reading

All AI Models Might Be The Same - by Jack Morris

blog.jxmo.io · 2,404 words · saved by 1 readers

It’s a guessing game, kind of like Twenty Questions. The funny name comes from the idea that, in the space of everything, ‘Mussolini’ and ‘bread’ are about as far away from each other as you can get. Thanks for reading Token for Token! Subscribe for free to receive new posts and support my work. One round might go like this: Is it closer to Mussolini or bread? Mussolini. Is it closer to Mussolini or David Beckham? Uhh, I guess Mussolini. (Ok, they’re definitely thinking of a person.) Is it closer to Mussolini or Bill Clinton? Bill Clinton. Is it closer to Bill Clinton or Pelé? Bill Clinton, I think. Is it closer to Bill Clinton or Grace Hopper? Grace Hopper. Is it closer to Grace Hopper or Richard Hamming? Richard Hamming. Is it closer to Richard Hamming or Claude Shannon? You got it, I was thinking of Claude Shannon. Hopefully you get the point. By successively narrowing down the space of possible things or people, we’re able to guess almost anything. How is this game possible? Mussol

All AI Models Might Be The Same What can language model embeddings tell us about understanding whale speech and decrypting ancient texts? On the Platonic Representation Hypothesis and 'universality' in AI models Jack Morris Jul 17, 2025 144 10 14 Share Project CETI is a large-scale effort to decode whale speech. If AI models do learn a universal language, we might be able to use it to talk to whales. Growing up, I sometimes played a game with my friends called “Mussolini or Bread.” It’s a guessing game, kind of like Twenty Questions. The funny name comes from the idea that, in the space of eve

Explore this link on the map →

related reading