Anthropic says no regression behind Claude Code usage complaints, blames heavy sessions
bcherny · x · 2026-10-29
Anthropic engineer Boris Cherny published the official findings on Claude Code's "usage draining too fast" complaints:
- The team reviewed all user-submitted session IDs and found a few smaller issues making some sessions burn tokens faster than they should; fixes are rolling out now.
- No single root cause and no regression in Claude Code. Most cases traced back to one or two heavy sessions: xhigh effort, /goal, Workflows, Agent Teams, or long SDK jobs.
- Tips: watch your effort level (subagents inherit it by default), use /usage to see where tokens go, and report anomalies via /feedback.
More from coding & agent
- "Never trust a benchmark you haven't cheated yourself": dev shows agent benchmarks favor whoever builds them — cnakazawa · 2026-10-29
- Retweeted thesis: Self-updating docs are an 'infinite market' like AWS — handotdev · 2026-10-29
- Vicki Boykis on how to learn ML in 2026: self-taught path and working with agents — vboykis · 2026-10-29
- Coinbase launches global AI trading competition with $2M prize pool — MurrLincoln · 2026-10-29
- vboykis: an agent eagerly helped me set an env var wrong and broke my results — vboykis · 2026-10-29
- Video pro: anyone claiming AI edits videos end to end is lying — juliey4 · 2026-10-29