I analysed 43 hours of my agents’ run history. The model took only 16% of it. The rest was tests,...
My AI agents got slower. Turns out the mess was mine
Related
My AI agents got slower. Turns out the mess was mine
I analysed 43 hours of my agents’ run history. The model took only 16% of it. The rest was tests,...
Claude Fable 5.2 migration for TypeScript backends
Claude Fable 5.2 migration guide for TypeScript: which parameters now return 400, how to catch refusals and when the model is worth its higher price.
Build an LLM Gateway with hikyaku: One Endpoint, AI-Picked Models and Failover Across Providers
Put one OpenAI-compatible endpoint in front of Gemini, Claude and OpenAI with hikyaku: a decision model picks the model and a failed provider falls back.