Teknium on Unify's memory research: Hermes shows both memorization and ~15% gain over finetuning
Teknium · x · 2026-11-12
Teknium comments on Unify's new research into Hermes' memory mechanism, arguing the results actually show both memorization (with memories being used) and generalization — a 15% improvement over finetuning at around 28%. He calls it interesting work with plenty of room to explore and plans to study the paper.
Related event: Teknium: Hermes Shows Both Memory and Generalization, ~15% Over Fine-tuning(2 posts)→
More from Research
- Possible eval leak: all frontier models fail a GPQA Diamond question whose official answer seems wrong — qberthet · 2026-11-12
- Latent Sparse Attention clusters KV values for 70x speedup over full attention — bendee983 · 2026-11-12
- Flash ALOHA masters precise robot manipulation with just 50 demos, fully open sourced — Thom_Wolf · 2026-11-12
- CARTBench from Zhejiang U & Xiaohongshu: no model tops 45% on excellent shopping advice — Yuqin Dai · 2026-11-12
- Math Benchmark Sheet Shows 90.43% Top Accuracy at Just $1.21 per Run — teortaxesTex · 2026-11-12
- e-means beats k-means in 1.4 epochs, delivering 10-45x GPU speedups on embeddings — pmttyji · 2026-11-12