mujia··on Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT)A cheaper model can look fine per request, but one weak answer may create another call or a human review step. That seems like the hardest cost to capture.
mujia··on Show HN: Spendict – a performance marketer's verdict for AI agents, over MCPHow much of the verdict comes from the ad itself,and how much from the account behind it?