Preprint: LLMs store numbers as curves and helices, but compute comparisons differently
tweetsatpreet · x · 2026-10-09
A new preprint finds that language models internally store numbers in geometric shapes like curves and helices, but don't always compute with those shapes. For comparing two numbers, the authors discovered a neat algorithm: lines per number combined geometrically — showing representational geometry and computational mechanism can diverge.
More from Research
- Ex-self-driving ML engineer writes long-form on the practice of semi-supervision — Visual_Ability · 2026-10-09
- RLVR misses 'all minimal correct answers' problems; new credit assignment doubles finds — thoma_gu · 2026-10-09
- Debunked: AI did not solve the Millennium Prize Navier-Stokes problem — gerardsans · 2026-10-09
- New open-source 3JSBench evaluates LLMs on generating coherent Three.js 3D assets — ycombinator · 2026-10-09
- Moonworks' Lunara: Sub-10B Diffusion Mixture Transformer Tops Aesthetic and Human Blind Evaluations — paper-crow · 2026-10-09
- Study: Local domains take 41.4% of AI citations in Brazil, 38.3% in UK across ChatGPT and Gemini — gaganghotra_ · 2026-10-09