[captnObvious]

I’ve used GPT-4 as a pair programmer actively for over 40 hours now. Using it to do things you have 90% of the solution for is a bit of a waste of time.

Using it to help trouble shoot errors in logs when you’re feeling frustrated, and get a basic framework up from scratch to start modifying toward the your goal are the best use cases I’ve seen. The ability to get yourself unstuck in minutes is life changing. The biggest constraint right now is short term memory loss. It can nearly always recognize on a second pass through what mistake it made.

Keep in mind 32kb token requests are already in beta… and 4kb requests are what you have access to now. So… the memory thing is potentially a dead point soon. Though at 6 cents per 1kb if it actually has to volley 32k over to you it’ll almost cost $2.00 based on current API pricing.

That 32k option would allow GPT-4 to hold every non-monolithic project I’ve ever worked on in working memory. The pertinent parts anyway, it wouldn’t need to read CSS files or imported modules unless it really gets forced down a specific rabbit hole.

This will be one more reason new projects won’t be monolithic architectures. Easier for the AI to help out.

[w4ffl35]

It's also good for putting together boiler plate classes and some other things. I had it code most of klotski for example and have used it pretty heavily in this project (and I think that is evident in the code)

https://github.com/Capsize-Games/airunner

[coder543]

$2/request seems a little ridiculous. I checked the pricing and you’re not wrong… I just feel like that kind of pricing will apply even more industry pressure to develop competition. Decent open source options would be nice too.