New podcast episode on the decision layer for coding agents: local models routing between code and LLM reasoning
TheZachMueller · x · 2026-11-06
The Superlinear podcast's new episode talks with Jev of TypeSafe about a new "decision layer" for coding agents—placing cheap, fast judgment between deterministic code and expensive LLM reasoning.
Topics covered:
- Fast browser-use loops, including thdxr's OpenCode demo
- Live feedback while you type, including rileybrown's real-time post analyzer
- Experiments with test selection and local decision models, plus how fine-tuning could work
- Model, reasoning-effort, skill, and tool routing
Core question: if cheap, fast judgment can sit inside agent loops continuously, how should agent systems be redesigned around it?
More from coding & agent
- Amazon research: self-distillation pushes weight memory to 59.9%, beating retrieval — omarsar0 · 2026-11-06
- Liquid AI's decision recipe matches Jev; new release adds on-device, modalities, primitives — helloiamleonie · 2026-11-06
- Decision models: general-purpose classifier or LLM? LoRA fine-tune wins — helloiamleonie · 2026-11-06
- LLMs are trained to predict next tokens, not make decisions — helloiamleonie · 2026-11-06
- Turn any LLM into a decision model with ~15 lines of inference-only code — helloiamleonie · 2026-11-06
- TypeSafe spent 2 years in stealth on Jev; open ecosystem copied it in under a week — helloiamleonie · 2026-11-06