LLM digit-multiplication progress: what big-number arithmetic tests actually measure
ctjlewis · x · 2026-10-29
The author recalls that in 2024, the frontier for LLM digit multiplication was around 32×32 for a 64-digit product. He argues LLMs won't run RISC-V or do bitwise arithmetic, so the point of these tests is to demonstrate the largest computation a model can perform. He finds the underlying memory technique the most interesting part.
More from Models
- GPT-6.1 Sol capacity limits stall overnight agent tasks after 45 minutes — CtrlAltDwayne · 2026-10-29
- Rumor: Anthropic reportedly has internal model beating Mythos 5.1 with better alignment — VraserX · 2026-10-29
- DIAL Benchmark Ranks Speech-to-Speech Models With 30k+ Human Ratings Across 9k Live Calls — sarahcat21 · 2026-10-29
- Benchmaxxing debate: is training on test despicable or the vertical AI superpower? — HanchungLee · 2026-10-29
- OpenRouter served 5.2T tokens in a day—back-of-envelope math questions where all the GPUs go — teortaxesTex · 2026-10-29
- Musk amplifies dev's list of AI 'wtf' moments, hailing Grok Bot as genuinely incredible — elonmusk · 2026-10-29