This week's°hard word primary goal°hard word is to test some new LLM-powered°hard word coding°hard word tools. ⚔️ well, actually, maybe the primary°hard word goal°hard word is the code°hard word they are writing?
First up: ZenCoder°hard word. ⚙️ https://zencoder.ai
----
ZenCoder°hard word is a VSCode°hard word plug-in°hard word. Which makes it similar to everything else.
The "Generate Unit Tests" agent°hard word is quite nice. 💡 it is so good that it reveals°hard word the limits of progress. Instead of spending°hard word 25% of the time writing tests, I spend°hard word 5% of the time, and get 3x the test coverage°hard word. But ... that's°hard word still only a 20% decrease in time. No matter how good it is. The remaining 5% of the time is spent°hard word reading the tests 🔥 it almost makes unit tests fun°hard word! 💡 of course, unless°hard word you're°hard word checking the tests, it doesn't°hard word matter if they are there
Everything else feels unremarkable°hard word compared°hard word to Claude°hard word. But, it has one key feature°hard word that "uploading°hard word files°hard word to the Claude°hard word web°hard word interface°hard word" does not°hard word: diffs°hard word in VSCode°hard word.
----
ZenCoder°hard word is $19/month. For ... an unknown amount of usage°hard word.
I am on the "two week free trial°hard word", and have not°hard word hit a usage°hard word limit yet°hard word. But there is no sign of what those limits are, or how close I am to it.