Anthropic probes Claude Code usage complaints, finds no regression, ships targeted token fixes
patience_cave · x · 2026-10-29
- Anthropic engineer @bcherny followed up on the community-submitted Claude Code session IDs: the team went through all of them.
- Conclusion: no single root cause and no regression in Claude Code; most reports of faster limit burnout traced back to one or two issues making sessions consume tokens unnecessarily.
- Fixes for those issues are rolling out now. One long-time user reports weekly completions dropping from 12 to 6 on repeated tasks, suspecting context rot, though Anthropic hasn't confirmed that attribution.
Related event: Anthropic Finds No Single Cause for Claude Code Usage Spike(3 posts)→
More from coding & agent
- Agents Use Your Codebase as Memory — and That Changes How You Should Write It — auto_grad_ · 2026-10-29
- Dev builds fully automated AI content farm, gains ~100 followers in 5 days — cneuralnetwork · 2026-10-29
- Effect 4.1 released: new crypto modules, Glob search, streaming CSV and HttpApi improvements — samgoodwin89 · 2026-10-29
- Prompting Cheat Sheet Breaks Down How to Use ChatGPT, Claude, Perplexity and Gemini — nikola_mr64990 · 2026-10-29
- Developer hails Google's rumored 'Carbon' model as first reliable vibe-coding model from Google — cgarciae88 · 2026-10-29
- opencode v2.2.1 ships /goal mode that runs agents until objectives are met — github-actions[bot] · 2026-10-29