As of: 2026-10-17 22:10 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/p/x-iamgrigorev-2111092000086724922/

# “Reflection Beam checkpoint is finally here and hence details of the architecture…”

George Grigorev (@iamgrigorev), X, 2026-10-16.
Source: https://x.com/iamgrigorev/status/2111092000086724922

## Archived text

> Reflection Beam checkpoint is finally here and hence details of the architecture
> 
> Several important observations
> 
> - 48 q heads, 8 kv heads, SWA-512, swa theta 10k (conceptually same as laguna :D )
> - pretty high aspect ratio 98.5 (not enough depth, harms reasoning)
> - 1:5 SWA:GA ratio! so swa goes first here and quite aggressive
> - 3 dense layers for stability
> - depth based residual add 
> - some modification of yarn for long context, not sure about it yet
> > Scalable-softmax query scale, `(1 + position / 2048) ** 0.1`, for layers that run without RoPE.

Archived 2026-10-17 via fxtwitter (unofficial).
Counts: 2,939 views, 59 likes, 1 repost, 2 replies (at fetch time)