Skip to main content

Tag

Engineering

2 articles tagged with Engineering.

← All articles

  1. Routing a prompt between Gemini Nano and the cloud

    Chrome and Edge both ship a language model, and the AI SDK makes swapping one for a cloud model a one-line change. The interesting part is the router that decides which one runs, and every constant in it comes from a measurement.

    AIGeminiLocal-firstTypeScriptEngineering

  2. MCP's Progressive Tool Discovery

    Progressive tool discovery is usually sold on prompt caching. Keep the tools array fixed, the argument goes, and the cached prefix survives. I ran 72 benchmarks across gemini-3.5, 3.6 and 3.7 Flash at 14, 42, 84 and 280 tools. The fixed prefix cached in exactly zero of 36 runs, the pattern it argues against cached up to 93%, and the point where the pattern starts paying moved down to about 20 tools on the newest model.

    AIMCPAgentsEngineeringTypeScript