How Anthropic made claude.ai 3x faster in two weeks with Claude, merging 3,000+ changes
trq212 · x · 2026-09-30
Anthropic's engineering blog details a two-week August sprint that made claude.ai and the desktop app 3x faster, run entirely from a single Slack channel with Claude in every thread.
Key numbers
- Focus: four journeys covering 95% of user activity
- P75 time-to-typeable-page: 3.1s → 0.55s
- New Claude Code session: 0.8s → 0.3s
- Claude Cowork cloud session load: 2.6s → 0.73s
- Estimated tens of thousands of user-hours saved daily
How it worked
- Claude Tag (beta) ran an internal research model roughly comparable to Opus 5.5
- Claude found bottlenecks, built benchmarks, shipped improvements, watched every deploy; humans set goals, made tradeoffs, approved changes
- 3,000+ merged changes with zero customer-facing incidents or rollbacks
Core method: "Once Claude can measure something, it can make it faster" — keep expanding what gets measured.
More from coding & agent
- Amp's Plaid mode runs GPT-6 Astra at 6x speed for a premium — OpenAIDevs · 2026-09-30
- Dan Grover: multi-agent 'personalities' are a conceit — different contexts suffice — DanGrover · 2026-09-30
- repligate on LLM spontaneity: let the model decide when its own API gets called — repligate · 2026-09-30
- OpenAI shares catch-up link for its full ChatGPT Plugin Extensions update — OpenAIDevs · 2026-09-30
- Year-long experiment pits Claude against the S&P 500 with a $1,000 paper portfolio — OriginalScrubLord · 2026-09-30
- ChatGPT Work and Codex desktop apps add PR-based code review with Codex — OpenAIDevs · 2026-09-30