Hand-computable AI? Markov chains plus polynomial feature fits for POS tagging
cephaloform · x · 2026-09-16
Asked whether AI could technically be computed by hand since LLMs are just math, cephaloform describes a fun toy approach: ensembling Markov chains for part-of-speech tagging with linear equation fits over polynomial combinations of a random 1D projection of semantic features, using 4 words of context. Trains in about an hour and is fun to sample.
Related event: Markov Chains Plus One-Dimensional Projections Enable Hand-Computable AI(3 posts)→
More from Fun
- Coffee shop owner harassed for ChatGPT menu poster exposes 'anti-AI mania' backlash — GabGarrett · 2026-09-16
- How the 'AI Doom' narrative went viral: it started with Harry Potter fandom — TinfoilTricorn · 2026-09-16
- Babysitting the coding agent in the terminal 'actually takes a lot of skill' — stephenroller · 2026-09-16
- Altmanstein meme pokes fun at wild GPT Astra projects shocking Sam Altman — cocktailpeanut · 2026-09-16
- Astra's MoE visualization looks like Christmas lights, quips researcher — vtabbott_ · 2026-09-16
- Inside a rationalist AI-doomer meetup: questioning 'AI kills everyone' got me walked out on — StewartalsopIII · 2026-09-16