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
What a language server does, and what it would add to code review
A walk through how a language server works inside, an experiment comparing it with a code graph on three real pull requests, and why saving its answers as an index file removes the memory cost.