User complains model takes four minutes to compare two 16-token completions
cephaloform · x · 2026-11-10
While digging into sample efficiency, the author reports severe inference latency: asking the model to compare two 16-token completions takes about four minutes to return, suggesting slowdowns run deeper than expected.
More from Models
- Andrew Carr reports 400 tok/s on Muse Ember — andrew_n_carr · 2026-11-10
- Claude Fable 5.2 scores 64.9% on RoboDojo robot control, dominating rivals — burny_tech · 2026-11-10
- Claude Fable 5.2 video demo wows on pacing, but AI-sounding music persists — jiayuan_jy · 2026-11-10
- Gemini Notebooks keeps pulling context from old conversations, user reports — AnonymousDork929 · 2026-11-10
- DavidAU releases Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF merge — mp3m4k3r · 2026-11-10
- Uncensored Gemma 4 31B 'heretic' build hits Hugging Face, 11.9GB quantized — alexcovo_eth · 2026-11-10