Practice · 2024–now · AI Present

Reasoning models for grep tasks

o1-class deliberation for tickets that needed a filter. Resume-driven inference.

Reasoning-model overkill failed as a default because expensive deliberation is not a substitute for clear specs and cheap tools. Frontier reasoning sticks on hard planning and math; it fades when every autocomplete call escalates to a thinking model. The fad was status; the stuck layer is model routing.

Cost of the fad

Thinking tokens burned on problems a SQL query and a unit test would settle. Latency and invoices grew; correctness did not.

Patterns

Context

Demos consolidate; evals remain

AI pair programming changed how code is typed faster than how it is reviewed. Agent frameworks and standalone vector stores sorted into demos versus durable plumbing; mid-market RAG folded back into Postgres. The permanent layer is familiar: evals that gate deploys, model routing for cost, tool protocols instead of plugin snowflakes, and humans who own production. Autopilot rewrites and vibe-shipped auth middleware are still big-bang migrations with better slides — and a longer on-call.

Compare with

Related

© 2026 Fadstack · Shane Code

Opinionated history · not a ranking