Episode Details

Daniel's AI-generated show deploys to Vercel, runs on serverless Postgres, and produces exactly the kind of wide-ranging content he wants. The problem is the feed — automatic tagging that started inventing its own categories, then duplicating them in ways nobody notices. This episode works through the fix: why unconstrained categorization never converges, how JSON Schema enums and context-free grammars make label bloat structurally impossible, and why a fine-tuned encoder beats a frontier model for a stable label set at one to two orders of magnitude lower cost. We also cover the counterargument — that a confident wrong classification is worse than no classification — and the read-at-classification-time pattern that dissolves the serverless redeploy problem entirely. Episode #860234 — open it directly at myweirdprompts.com/860234