The terminal-based tool originally evolved from internal safety research.
The terminal-based tool originally evolved from internal safety research.
@bcherny I could care less. You are working for an evil company.
@bcherny You guys are doing a fantastic job!
Anthropic just published the story of Claude Code and that how Boris Cherny went from 10% AI-written code in 2025 to 100% in 2026. Research kept improving agentic coding through shells, file search, code execution, and edit loops. In 2024, Boris Cherny’s Claude CLI prototype was the first real terminal product in this direction. A small team shipped fast, used Claude Code to build Claude Code, and fixed feedback quickly. The 2025 launch was buggy at first, but Claude Sonnet 4 and subscriptions made it take off.
This is our first time telling the story of how we first built and launched Claude Code, starting with its origins in Anthropic safety research. So much more to do. We are 1% done. https://twitter.com/claudeai/status/2074244664199115201
a retrospective on making claude code from our early team! https://twitter.com/claudeai/status/2074244664199115201
Ask a question below.
Published answers will appear here.
