Cactus routes prompts with Gemma 4 confidence scores, cutting cloud calls to 15%–55%
GlennCameronjr · x · 2026-07-29
Cactus says it solved hybrid routing by post-training Gemma 4 to emit a confidence score for every prompt.
- High-confidence prompts are handled locally.
- Low-confidence prompts are routed to a larger cloud model.
- The company says routing only triggers 15%–55% of the time, depending on the domain benchmark.
The post is a short note on a practical hybrid-model design, not a full technical write-up.
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16