If AI coding is lowering your code quality, you're not managing quality right
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
If AI coding is lowering your code quality, you're not managing quality right
Unofficial Hacker News client; not affiliated with Y Combinator.
zahlman · · focus · HN ↗
> Instruct the agent to think through the test scenarios and test cases based on the requirements, Write the test cases, Write the implementation, Test the implementation against the test cases and fix any issues that come up, Maybe backfill any remaining coverage gaps—but again, keeping the requirements in mind.
It's too easy, in general, to write tests that simply mirror the implementation. I wonder if it would be better to spin up two sub-agents to attempt test cases and implementation in parallel, so that neither poisons the other's context.