Two years of experiments on model arithmetic beat most academic literature, author says

ctjlewis · x · 2026-09-28

Follow-up in the same thread: the author shares the general form of the multiplication algorithm and argues this work is cooler than 99% of academic literature, which he says is disproportionately focused on what models supposedly cannot do. The paper will cover two years of computational experiments across several generations of models.

Related event: Visualizing Claude Opus 4.6's Internal Multiplication: Two Years of Experiments Become a Paper(6 posts)→

Original post →

More from Research

Research channel →