News for hackers. Stuff that matters.
Re:Can GPT-4 *Actually* Write Code? by theK on Friday March 17, 2023 @02:47AM (#35194025)
On the flip side, I am having a great time charging enterprises exorbitant hourly rates to come in and help them fix their crappy crud programms.

But I still don’t know if I am thrilled by the prospect of being called in to make their monkeypatched, GPT generated project work.

Re:Can GPT-4 *Actually* Write Code? by anonzzzies on Friday March 17, 2023 @03:18AM (#35194229)
> their monkeypatched

You mean, like almost every outsourcing company pops over? So the type of code that infests companies who hired some sweatshop to do ‘some simple crud’? What’s the difference? Can you see the difference? Besides the gpt code will be far better commented as comments come for almost free with gpt while humans hate writing them.

Re:Can GPT-4 *Actually* Write Code? by theK on Friday March 17, 2023 @03:41AM (#35194361)
I think you can trust the code of both those worlds exactly the same, not at all.

I’ve seen GPT 3 and 4 hallucinate the most amazing commentary about their own output. Maybe we will get dependable, out of process, guidance at some point about how factual the model thinks it is on an output per output basis but until that point you should trust every LOC and comment exactly the same as code gifted to you by an adversary.

My modest 2¢

Re:Can GPT-4 *Actually* Write Code? by pms on Monday March 20, 2023 @02:10PM (#35235976)
Exactly... and then the question becomes: why do I interact with an adversary?
Re:Can GPT-4 *Actually* Write Code? by amrocha on Friday March 17, 2023 @07:54AM (#35195822)
I'm working on an outsourced codebase right now and boy, I wish they hadn't commented their code at all
Re:Can GPT-4 *Actually* Write Code? by hnfong on Friday March 17, 2023 @02:55AM (#35194088)
"Hey GPT-X: Can you refactor the codebase in [email protected] for me? Preferably in the style of [email protected] that I worked on last year."
Re:Can GPT-4 *Actually* Write Code? by theK on Friday March 17, 2023 @03:11AM (#35194179)
Token cap will probably be the biggest problem here.

After validation.

After getting the changes to disk, documented, actually compiling, etc…

But the biggest problem is that transferring the nuance that is external to the code base is typically really tiresome and lengthy grunt work and again token cap.

Re:Can GPT-4 *Actually* Write Code? by anonzzzies on Friday March 17, 2023 @03:19AM (#35194237)
They went from 4K to 32k in a few months. Wait a few years.
Re:Can GPT-4 *Actually* Write Code? by theK on Friday March 17, 2023 @03:34AM (#35194327)
Few years, yes. I’m with you “the change is coming” but we still need to transfer millions of tokens in and out to cater for context and out of repo intricacies.
Re:Can GPT-4 *Actually* Write Code? by anon7725 on Friday March 17, 2023 @12:31PM (#35199311)
Large enterprises will just pay to fine tune over their documents/code/etc.
Re:Can GPT-4 *Actually* Write Code? by Jensson on Friday March 17, 2023 @03:20AM (#35194245)
GPT-3 is 3 years old, not a few months.
Re:Can GPT-4 *Actually* Write Code? by anonzzzies on Friday March 17, 2023 @03:27AM (#35194291)
Sure but the token jump to 32k is new isn’t it? Even 8k to 32k is significant and that was this year.
Re:Can GPT-4 *Actually* Write Code? by Jensson on Friday March 17, 2023 @03:32AM (#35194313)
Yeah, but the jump to 32k didn't take a few months, it was years in the making. Otherwise you could extrapolate with "yesterday we had 4k, today we have 32k, tomorrow we will have 256k", that isn't how we do it. If we follow the same exponential pace 256k would have to wait 3 years, and even that is unlikely.
Re:Can GPT-4 *Actually* Write Code? by osigurdson on Friday March 17, 2023 @07:59AM (#35195878)
I think it is better to assume that we are at the beginning of the s-curve, not the end.
Re:Can GPT-4 *Actually* Write Code? by osigurdson on Friday March 17, 2023 @11:05AM (#35198008)
Wow. I never expected to be downvoted for such a comment. Downvotes please elucidate as to why we are in the asymptomatic phase with LLMs.
Re:Can GPT-4 *Actually* Write Code? by hnfong on Friday March 17, 2023 @10:48PM (#35205565)
"Luddites" refusing to accept that we might be onto something that is going to change humanity forever...

The sad thing is that real luddites would go out and actively sabotage AI development because they think it's a real threat. Yet these people just makes bold and false claims in online forums and continue to move the goalposts once they're proven wrong. Sad. Pathetic. (and obviously, I don't mind being downvoted. Whatever! :)

Re:Can GPT-4 *Actually* Write Code? by anonzzzies on Saturday March 18, 2023 @05:00AM (#35207442)
Seems very man of these here for some reason, trying to find whatever reasons and ways (gonna be licensing mostly) to spread FUD.
Re:Can GPT-4 *Actually* Write Code? by riku_iki on Friday March 17, 2023 @02:52PM (#35201282)
we don't know what that jump means, did they increased model proportionally, or slapped some projection layer with quality degradation?..