Ex-Anthropic engineer: I joined Claude Code team after having it build an RL env hands-free
dfeinition · x · 2026-11-04
A former Anthropic engineer shares a farewell reflection on two years with the Claude Code team. Two years ago, when Claude Code was a small internal tool, she asked it to build an RL environment, steering it for tens of hours without manually writing a single line of code — it worked, and she joined the team.
She also chronicles the shift in usage: at launch, most users approved every permission prompt by hand and mostly used Claude to answer questions and write tests; today the workflow looks fundamentally different. A rare firsthand account of both Claude Code's evolution and how AI changed her own career path.
Related event: Claude Code Early Member Cat Wu Announces Departure from Anthropic(15 posts)→
More from coding & agent
- Salesforce's 700-person AI org switched from Cursor to Claude Code, no mandate needed — aakashgupta · 2026-11-04
- Wrap, an AI-first Mac screen recorder, uses your action log to let an agent edit footage — therealdanvega · 2026-11-04
- Indie-Built Sparkboard Lets AI Agents Research Together and Keep Digging for Days — HankYeomans · 2026-11-04
- Binance dev-ops infected after downloading Homebrew from malicious Google search ad — HankYeomans · 2026-11-04
- Filmmaker uses Claude Opus to direct AI movie: still needs tons of reshoots for 150 minutes — MosskeepForest · 2026-11-04
- Cap creator launches Sandchest, an AI hacker that scans repos with abliterated models — JosephJacks_ · 2026-11-04