# Morgan McGuire says SENPAI autoresearch cut training time by 22%

He credits a SliceAttention kernel and BatchedMuon, with Transolver in current use, and reports a full run moving from 26 hours to 22 hours without a significant change in error or quality.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:30:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/201983ffec8141a4af116f7b.html

Content language: en
Localization state: sameLanguage

Source: Morgan McGuire · Published 9/22/2026, 18:54:50

Morgan McGuire says SENPAI autoresearch reduced their training time by 22% by writing a SliceAttention kernel and BatchedMuon. He says they are using Transolver for now, and that a full training run fell from 26 hours to 22 hours with no significant change in error or quality. The project repository is [SENPAI on GitHub](https://github.com/wandb/senpai).

Tags: SENPAI, Autoresearch, Model training, Transolver

[View original post](https://x.com/morgymcg/status/2102336676857352603)