I decided today to take a look at CloudFlare’s new OAuth provider library, which they apparently coded almost entirely with Anthropic’s Claude LLM: This library (including the schema documentation) was largely written with the help of Claude, the AI model by Anthropic. Claude’s output was thoroughly reviewed by Cloudflare engineers with careful attention paid to security and compliance with standards. Many improvements were made on the initial output, mostly again by prompting Claude (and review...