Anthropic engineer on Claude Code effort levels: low for staying in the loop, max for security audits
trq212 · x · 2026-09-26
Anthropic engineer trq212 published a deep dive on effort levels in Claude Code: the newest Claude models respond to effort without breaking the prompt cache, but users are unsure which level to pick. His practice: effort low is used a lot when staying in the loop; effort max is basically only for fully hands-off runs or hunting security vulnerabilities. The article digs into evals to explain why effort exists and how models behave at each level.
Related event: Anthropic Explains Claude Code Effort Setting(4 posts)→
More from coding & agent
- "Coding is solved": dev says he never reads a single line, relies on model audits — Yamapama · 2026-09-26
- mitsuhiko agrees Agent hype mirrors the OC hype cycle from eight months ago — mitsuhiko · 2026-09-26
- Kev: open-source Jev-like decision models from 0.8B to 27B run locally for free — alexcovo_eth · 2026-09-26
- Having AI build its own asset creation tools first pays off for 3D scene generation — gandamu_ml · 2026-09-26
- Tev1 0.8B open-sourced: a tiny Jev-like classifier running locally on Mac at ~50ms — iamrobotbear · 2026-09-26
- Armin Ronacher: with agents this good, Rust devs should stop fearing unsafe — mitsuhiko · 2026-09-26