[ehnto]

Code you didn't write is an even bigger liability, because if the AI gets off track and you can't guide it back, you may have to spend the time to learn it's code and fix the bugs.

It's no different to inheriting a legacy application though. As well, from the perspective of a product owner, it's not a new risk.

[zarzavat]

Claude is a junior. The more you work with it, the more you get a feel for which tasks it will ace unsupervised (some subset of grunt work) and which tasks to not even bother using it for.

I don't trust Claude to write reams of code that I can't maintain except when that code is embarrassingly testable, i.e it has an external source of truth.

[shaisjsh]

> some subset of grunt work

What tasks are these? I don’t doubt they’re out there, but if I know the exact code that needs to be generated typing speed is not a bottle neck.

For me the slow part is determining what to write. And while AI helps with that (search, brainstorm, etc) by the time I know what to write trying to get the AI to enter those lines is often just a slow down. Much like writing up a ticket for a junior, I could write the code faster than I could write the English language rules describing how to write that code.

[Frannky]

There is no generated code. It is just a user interacting with a CLI terminal(via librechat frontend), guided by Markdown files, with access to MCPs

[abraxas]

Fascinating. Do you have a longer writeup about it or an example repo for me to understand exactly how it fits together?