Have they implemented "I don't know" yet.
I probably spend 100$ a month on AI coding, and it's great at small straightforward tasks.
Drop it into a larger codebase and it'll get confused. Even if the same tool built it in the first place due to context limits.
Then again, the way things are rapidly improving I suspect I can wait 6 months and they'll have a model that can do what I want.
I agree. I use it a lot but there is endless frustration when the C++ code I am working on gets both complex and largish. Once it gets to a certain size and the context gets too long they all pretty much lose the plot and start producing complete rubbish. It would be great for it to give some measure so I know to take over and not have it start injecting random bugs or deleting functional code. It even starts doing things like returning locally allocated pointers lately.
> Then again, the way things are rapidly improving I suspect I can wait 6 months and they'll have a model that can do what I want.
I believe this. I've been having the forgetting problem happen less with Gemini 2.5 Pro. It does hallucinate, but I can get far just pasting all the docs and a few examples, and asking it to double check everything according to the docs instead of relying on its memory.
I wonder if documentation would help to create an carefully and intentionally tokenized overview of the system. Maximize the amount of routine larger scope information provided in minimal tokens in order to leave room for more immediate context.
Similar to the function documentation provides to developers today, I suppose.
It does, shockingly well in my experience. Check out this blog post outlining such an approach, called Literate Development by the author: https://news.ycombinator.com/item?id=43524673
Have you tried using a tool like 16x Prompt to send only relevant code to the model?
This helps the model to focus on a subset of codebase thst is relevant to the current task.
(I built it)
Just some tiny feedback if you didn’t mind; in the free version 10 prompts/day is unticked which sort of hints that there isn’t a 10 prompt/day limit, but I’m guessing that’s not what you want to say?
Ah I see what you mean. I was trying to convey that this is a limitation, hence not a tick symbol.
But I guess it could be interpreted differently like you said.
bahahaha spoken like someone who spends $100 to do the task a single semi decent software developer (yourself) should be able to do for... $0
It's a matter of time.
The promise of AI is I can spend 100$ to get 40 hours or so of work done.