PSSA: A non-transformer language model written from scratch in Rust
Why CEREBRO kept it
Novel LLM architecture in Rust, agentic-relevant
The text below is an automated extraction of the article at https://github.com/Sparticle62ops/pssa, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
PSSA is a small language model that is not a transformer. It reads text one token at a time through a recurrent state-space layer, keeps a bank of episodic memories it can look things up in, and rewrites part of its own weights while it runs. It is written in Rust from scratch, with no PyTorch, no TensorFlow, and no ML framework of any kind underneath it. At matched parameters and on the same corpus, it learns faster than a transformer and generates text about twelve times quicker on the same CPU. Not for speed points, and not because the language makes the architecture better. PSSA needed per
Community take
RNN with zero novelty; Rust framing is clickbait that blocks proper PyTorch/GPU validation.
Who builds this
Sparticle62ops is profiled here from public GitHub push activity.
Backlinks
Appeared in 1 briefing