Comment by maipen
9 hours ago
You still need to give it precise context and instructions when dealing with things that are not web apps or some other software cliche.
The reasoning is great in opus, unbeatable at the moment.
I understand what you mean, it becomes disappointing on more niche or specific work. It’s honestly a good thing to see these models are not really intelligent yet.
I still don't trust any AI enough to generate or edit code, except for some throwaway experiments, because every time I tried it's been inefficient or too verbose or just plain wrong.
I use it for reviewing existing code, specifically for a components-based framework for Godot/GDScript at [0]. You can view the AGENTS.md and see that it's a relatively simple enough project: Just for 2D games and fairly modular so the AI can look at each file/class individually and have to cross-reference maybe 1-3 dependencies/dependents at most at any time during a single pass.
I've been using Codex, and it's helped me catch a lot of bugs that would have taken a long time on my own to even notice at all. Most of my productivity and the commits from the past couple months are thanks to that.
Claude on the other hand, oh man… It just wastes my time. It's had way more gaffes than Codex, on the exact same code and prompts.
[0] https://github.com/InvadingOctopus/comedot
I had a similar experience and the answer appears to be learning how to use a specific model for a specific task using a specific harness (model X task X harness). Another, and somewhat related, lesson learned is understanding how to work with a given model and not against it.
I still get really mad at AI sometimes and I am not sure whether I could use AI for coding full time.
(Codex broke my git a few days ago.)