Auto-research with Opus 5.5 and GPT6 Astra yields explicit fast matmul schemes on GitHub
IgorCarron · x · 2026-10-18
Researcher AntoineTilloy open-sourced explicit-matmul-schemes, the output of an auto-research experiment using Opus 5.5 and GPT6 Astra to hunt for explicit fast matrix multiplication algorithms. The goal: test whether insights from record asymptotic constructions built on the Coppersmith-Winograd tensor can yield practical explicit rational square-matrix schemes, with exact coefficient access, proof witnesses, and literature comparisons. IgorCarron's take: whether these schemes can be substantially improved decides if fast matrix multiplication will ever be practically relevant.
More from Research
- Paper argues mechanistic interpretability needs a rigorous "logic of inference" — burny_tech · 2026-10-18
- NeurIPS 2026 Journal Track accepts 88 papers from TMLR, JMLR, AoS — NeurIPSConf · 2026-10-18
- RCT: AI-generated layperson summaries of medical findings improve visit quality and shorten consultations — EricTopol · 2026-10-18
- Progress on mapping jev's j-space — sloppenheimer · 2026-10-18
- Hand-probing tiny model neurons: gate is swappable, down steers it into an owl — maxsloef · 2026-10-18
- MIT paper builds attention-based foundation model for quantum states, 18 training points suffice — jwt0625 · 2026-10-18