Dev slams 'speed-maxing' trend: chasing tokens/s at the cost of output quality
casper_hansen_ · x · 2026-10-08
Developer casperhansen criticizes the recent 'speed-maxing' obsession: quality defines a model, and trading quality for higher tokens/s just produces more slop to clean up, citing Qwen3.8-27B's loyal users as evidence that quality is what keeps people coming back.
More from Models
- Hours after Reza Zadeh's post, OpenAI announced a 2.25 result on its math benchmark — Reza_Zadeh · 2026-10-08
- AI2's Bolmo tackles the 'token tax' hitting Global South scripts — Kyle_L_Wiggers · 2026-10-08
- Grok bot goes proactive on X, now suggests what you should do next — Daniel_Farinax · 2026-10-08
- OpenAI and Cloudflare launch decision APIs — tested at 355 decisions, TypeSafe's Jev still decides more — PawelHuryn · 2026-10-08
- Gary Marcus: OpenAI's vague math report 'would never pass peer review' — Tao responds too — Gary Marcus · 2026-10-08
- d1-3B runs on a MacBook: hands-on demos show Liquid AI's open model in action — JosephJacks_ · 2026-10-08