Claude Code team member leaves Anthropic
The departing team member says Claude Code now handles large migrations and builds new products.
TLDR
The team member recalled steering an early version of Claude Code for tens of hours to build a reinforcement learning environment without manually writing code. They said that at launch, most people approved every permission prompt by hand and mainly used Claude for questions and tests. By the time they left Anthropic, they said, the default was trusting Claude’s judgment to auto-approve.
Combined views
360.8K
23 Sources, first seen ago


