Modal's Runtime event featured Cat Wu of Claude Code and Dax Raad of OpenCode discussing how code reviews, token spend, and hiring change when agents write most code. Topics include token spend at 1 to 2x payroll, turning every incident into a code review eval, and hiring for product taste over 10x execution.
What happens to code reviews, costs, and hiring when agents write most of the code?
At Runtime, @_catwu (Claude Code) and @thdxr (OpenCode) got into:
→ Token spend at 1 to 2x payroll
→ Turning every incident into a code review eval
→ Why “way too many people” use the terminal
→ Hiring for product taste over 10x execution
Source: Modal · x.comPublished · added here
