Stop using LLM prose for routing: Jev returns structured decisions at $0.042 per million tokens
mikegiannulis · x · 2026-09-18
The author calls out an absurd pattern: asking a model that can write novels "which bucket does this message go in?" then parsing generated text. TypeSafe AI's Jev skips the prose entirely, returning choices, scores, and probabilities directly — at $0.042 per million input tokens with free output.
Related event: Jev Outputs Structured Decisions Directly at $0.042/M Tokens(2 posts)→
More from coding & agent
- 15 harnesses, same result: informal test concludes agent harnesses don't matter — airesearch12 · 2026-09-18
- 4 deployment strategies explained via 4 visuals: feature toggle, blue-green, canary — _jaydeepkarale · 2026-09-18
- ServerKit: open-source server panel for apps, DBs and Docker hits 1.3k stars — tom_doerr · 2026-09-18
- Gary Marcus: Agents hold production credentials in a security gap nobody owns — GaryMarcus · 2026-09-18
- Amp's design philosophy: simple primitives, no tricks, let models improve it — HankYeomans · 2026-09-18
- You.com wraps AI Agentic Hackathon with self-improving agents challenge — PolarBearby · 2026-09-18