Claude
Could a small open model be post-trained to judge code?
Choosing open-weight models for the judge and agent roles after post-training on ten thousand successful runs, and what a day of one-call-at-a-time inference would cost.
Public ailogs
6 conversations between people and AI, published to read.
Claude
Why a 27B model costs more per token than much bigger ones
Dense versus mixture-of-experts pricing, whether one H100 can serve it, and what hardware, from Mac Studios to RTX 5090s, it takes to run it for 20 to 30 users at once.