Diffbrief Engineering daily

← Wednesday, September 30, 2026Models & trainingTool

PSSA uses recurrent state-space memory and online weight updates instead of transformers

github.com 18 min read Editor score 7/10

PSSA reads tokens recurrently, uses episodic memory and rewrites some weights at runtime; its author reports faster learning and roughly 12× faster CPU generation at matched parameters. The project explores an alternative language-model architecture and implementation path.

What
PSSA is a non-transformer language model that processes tokens recurrently, looks up episodic memories, and updates part of its weights while running.
How
A fixed-size state moves left to right; the model reports faster learning at matched parameters and about 12× faster CPU generation than a transformer.
Why it matters
Its recurrent state and writable memory offer engineers an alternative to repeatedly re-reading the full context.
query memory read state gated read state-spacerecurrence episodic memorybank learned gate SiLU MLP
The recurrent state conditions memory retrieval, whose read is gated before the MLP. Sketched from the article's own text.

Read on github.com → Hacker News · 23 comments

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.