Hacker News Reader

don't forget: tests also inform the agent on what the code is _supposed_ to do. So with the cycle, you end up with 3 different potentially robust ways to look at and understand how to extend.

Context then is: docs, code and tests. Rather than try to build some omniscient agent, the context is built where the agent needs it.

View on HN

I agree that ensuring testing is the basis for modifying code in _future_ development (including understanding it). My problem is that we can't produce a study showing that TDD is producing better results _now_.

TDD doesn't help the agent figure out what it is supposed to do now- it is already writing the code and now and it must know what it is supposed to do to write it.

I am trying to use evidence-based approaches. I am only observing better results and tweaking now, but I plan to benchmark when tweaking is done.

Reply on news.ycombinator.com