[jbreckmckye]

I actually kind of do the opposite to most developers.

Instead of having it write the code, I try to use it like a pair reviewer, critiquing as I go.

I ask it questions like "is it safe to pass null here", "can this function panic?", etc.

Or I'll ask it for opinions when I second guess my design choices. Sometimes I just want an authoritative answer to tell me my instincts are right.

So it becomes more like an extra smart IDE.

Actually writing code shouldn't be that mechanical. If it is, that may signify a lack of good abstractions. And some mechanical code is actually quite satisfying to write anyway.

[wreath]

I actually started doing this for side projects that I use as a vehicle for learning and not necessarily to solve a problem and it's been great. 1) I don't feel like I just commissioned someone to do something and I half-ass checking it and 2) I actually do learn about new stuff as well even though sometimes it distracts me from the goal (but that's on me)

[randomNumber7]

Idk what models you are using. I'm pretty sure I tried the best avialable and arguing with them about pointers in non trivial cases seems like a recipe for disaster.

> Sometimes I just want an authoritative answer to tell me my instincts are right.

You realize that LLM answers highly depend on how you frame your question?

[Exoristos]

They also depend on several categories of chance circumstance.

[jbreckmckye]

> You realize that LLM answers highly depend on how you frame your question?

Of course I do. I'm not a moron.

In these cases, I already know the most likely answer to my question. The LLM just helps me reduce my self doubt