Model Effort Routing Remains Unreliable
zeeg · x · 2026-07-11
The author agrees with a previous point but points out that routing is currently unreliable.
The main argument is that when selecting effort levels like low / medium / high / x-high / max for a model, it is very difficult in reality to accurately judge the required compute or "effort" before a task begins; manually monitoring and adjusting it mid-task is also far from ideal. The author believes a better approach would be for the model to autonomously decide if it needs to scale up the effort level during execution.
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11