riscoss63/sillage

Your language model forgets everything. Sillage gives it a 4 MB memory that persists across sessions, no gradients, no fine-tuning, no growing index. Beats an unbounded kNN-LM at 1/13 the storage (perplexity 31 → 17). CPU-only, fully reproducible, four preprints with Zenodo DOIs.

4 best points · 0 comments · 1 Hacker News post · 6 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Sillage a 4 MB memory that lets a frozen language>model remember (4 points, 0 comments, by riscoss, 2026-08-25)