
A router that can't see the conversation can't classify "yes"
LiteLLM ran 5,600 live classifier calls to answer one question: how much of the conversation does a model router need to see? On the follow-ups that only make sense against history, agreement went from 14% to 78% — and the completion bill more than doubled, because two thirds of them had been going to the cheapest model.

Spec-Driven Development: is it the solution to Vibe Coding?
A GitHub toolkit with 127k stars says you should write the spec before the code, and let the agent build from it. I ran it, then read the two engineers who tested it properly — and both reached for the same comparison: the last time our industry tried generating code from documents.

GPT-5.6: OpenAI's new pitch is cheaper per task, not just smarter — verify it on your workload before you switch
GPT-5.6 (Luna, Terra, Sol) ships with a claim aimed straight at your bill: frontier coding scores on half the output tokens. What that means for agent economics, why you should verify it on your own workload — and how to build so model choice stays a config change.