Char-level models plus ngram or canon layers 'are the future', dev claims
cephaloform · x · 2026-09-13
- cephaloform follows up his char-level model remarks, claiming char-level models combined with ngram or canon layers represent the future direction.
Related event: Developer Praises Char-Level Models: No Retokenization Bugs(2 posts)→
More from Models
- Anthropic's policy details exactly when your Claude chats are used for model training — austinc3301 · 2026-09-13
- GPT-Live-1 first impressions: most natural voice model yet, but instruction following is unreliable — kolchinski · 2026-09-13
- GPT-6 Astra dethrones Gemini 3.8 Flash as the best vision model in side-by-side tests — Roger_M_Taylor · 2026-09-13
- Devin SWE-2 first impressions: fast and cheap, but shorter endurance than Codex — CtrlAltDwayne · 2026-09-13
- Different LLMs fail SWE tasks in distinct ways, dev observes — zainhas · 2026-09-13
- Training opt-outs may be a loophole: opted-out data could still improve models — logicus · 2026-09-13