Dev uses small model to triage resumes, cutting tokens so much it's given away free
draginol · x · 2026-09-21
Developer draginol says a new build is coming: a model called Jev intelligently triages resumes instead of a general LLM, and with @typesafeai it saves thousands of tokens — cheap enough to give away free to Clairvoyance subscribers. Jev even worked around an instruction bug that Claude Opus introduced. A nice example of cost optimization via model tiering.
Related event: Jev: smart resume screening so cheap developers can give it away free(2 posts)→
More from coding & agent
- Google open-sources Agent Substrate on GKE: 10x container density, sub-500ms agent resume — dl_weekly · 2026-09-21
- evmscope MCP server ships 20 blockchain tools for AI agents across 5 EVM chains — modelcontextprotocol · 2026-09-21
- The Latent Space adds agent registry, Elo duels and x402 credit economy — modelcontextprotocol · 2026-09-21
- Ex-GitHub Copilot engineer: coding agents speed everything up, yet leave us more work than ever — rakyll · 2026-09-21
- Codex limits draining 5x faster with 18% less usage, dev's tracking claims — StewartalsopIII · 2026-09-21
- ChatGPT co-creator's Jev: batch decisions without long LLM calls — DrDatta_AIIMS · 2026-09-21