Will a day come when AI knows how to do what it is told?
It's true that it often inserts placeholders.
You can try using the functions feature (via the API) and/or fine-tuning .
If it's relatively simple code then you could also look into Codellama or WizardCoder which you may also fine-tune.
To be fair, the instruction following capabilities of GPT-4 are absolutely incredible relative to what was available a few years ago.
Don't worry, it will only be a few more years before AI is able to completely replace you. Then you will be wishing you could go back to the time when you had to write an extra prompt to fill in the TODOs.
Larger and more sophisticated models will do the party trick more convincingly... but actually following instructions will require a different approach.
Yes it can, with robust system prompts.
The webapp is a misleading representation of ChatGPT's capabilities.
The other thing that I would really like to see is at least an option for deterministic responses. I like the creativity of ChatGPT constantly giving different responses but it is hugely problematic when you are trying to iterate and it keeps completely changing the thing you are iterating on.
The guy has NO IDEA what the group was actually talking about but it doesn't matter anyway. You can give him more context but all he can do id further tailor his story to try and fit in better with the group discussion.
I think people get confused about what LLMs are doing because you CAN ask the drunk guy questions and he CAN kind of answer, or ask him to do a party trick and he can kinda do it, but all he is doing is continuing the context you give him, he IMMEDIATELY forgets anything you told him so he can't do the same exact thing twice.
Not happy about it either.