Anthropic engineer: crank Claude's effort setting for risky code, dial it down for routine tasks
every · x · 2026-09-25
Every highlights advice from Anthropic's trq212 on Claude's effort setting: raising it gives the model more budget to think, test, and verify. For tasks like an HTML sanitizer—where code can fail in many ways—extra checking is worth the tokens. For coding tasks the model already handles reliably, low or medium effort suffices. Links to Every's Opus 5.5 Vibe Check included.
More from coding & agent
- Cursor mulls killing Plan Mode for a Shift+Tab effort-level hotkey — steipete · 2026-09-25
- Is the Opus 5.5 hype legit? A dev argues one-shot demos don't reflect real workflows — MrET97 · 2026-09-25
- Dev burns 5-10B tokens a day running 24 Devin agents plus Codex and Claude Code — teropa · 2026-09-25
- Question's Gambit tops BrowseComp-Plus recall with 96.6% using only BM25 — CShorten30 · 2026-09-25
- Engineer tests now bait AI tools with plausible-but-wrong answers to grade verification skills — l4rz · 2026-09-25
- AutoScientists NeurIPS paper: self-organizing AI research teams hit 74.4 percentile on BioML-Bench — marinkazitnik · 2026-09-25