LLMs Are Too Big: Aronchick on Right-Sizing Models for Log Routing
aronchick · x · 2026-09-22
David Aronchick argues we over-ask of AI: general-purpose LLMs are routinely tasked with narrow jobs like deciding whether a log line deserves human attention, then constrained to stay on task. Using Jev for log routing at Expanso convinced him tasks are often smaller than models — capabilities for Navier–Stokes aren't needed to route an INFO-labeled config reload. His thesis: pick models sized to the job, not the biggest one available.
More from coding & agent
- Cua Hits 25K GitHub Stars, Puts Claude Code Inside Legacy Desktop Apps — mhdfaran · 2026-09-22
- Cua Puts Claude Code to Work Inside Legacy Desktop Apps With No API — mhdfaran · 2026-09-22
- User Claims Codex Sol Hit by Shrinkflation as Quotas Quietly Shrink — StewartalsopIII · 2026-09-22
- Microsoft's BI-Bench: Frontier LLMs Score Under 50% on End-to-End Business Intelligence — MicrosoftResearch · 2026-09-22
- Dev packages hand-built MCP client into a Spring Boot 4 starter in one dependency — therealdanvega · 2026-09-22
- One-Prompt Call of Duty Clone Hits 20M Views: Inside the Gauntlet Loop Agentic Workflow — mattshumer_ · 2026-09-22