Am i the only one that tried using gpt4 for serious development work but stopped pretty fast because of its obvious limitations ?
Reading that article makes me wonder if we're even talking about the same thing.
Reading that article makes me wonder if we're even talking about the same thing.
1. API, concepts, etc docs with explanation. Much faster then googling then scrolling through tons of texts with blinking adds
2. Write simple things that I don't want to think about. Like in Python process all files in a directory, follow the links. Saves time.
3. Try things I don't know how to do. The recent was checking if user pressed a key without blocking in Python. Nontrivial, but possible. We went through several options till found the one which works on Ubuntu.
So, it's useful, no regrets about subscribing. Funny thing I'm using it working on toy GPT
I have used several of 'the big' SaaS GPTs, and have gotten great use from them.
There is absolutely a use for these tools, but they do take some small amount of skill to get good results.
It all comes down to the context you can provide to steer the answer to what you really need. The better you can describe your current state and what you want from the answer, the better the answer will be.
My only use so far is get inspiration for type naming, and very simple scripts that i'm too lazy to write myself.
But this happens less than once a month.