Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Isn't as Good at Coding as We Thought

pcmag.com

Post reply on HN
Print view View original

41–48 of 48 posts

Re: ChatGPT Isn't as Good at Coding as We Thought

#41

Post by namaria »

ChrisRR wrote: post #7
namaria wrote: post #6

I don't understand why generating language, or code, would be a good thing. Language, and code, is a tool for communication. If you treat it as fodder or merchandise, you loose the main use: transport meaning between different people. I fail to understand why we would want automatically generated language at all, except for the fact that you can sometimes make money off of it. Considering we're where we are as a civi…

You can't understand why software that can do in a fraction of a section what a human would do in hours would be valuable?

You're describing automation. I'm talking about a very specific subset of it: automatically generating human or (human readable) language.

Re: ChatGPT Isn't as Good at Coding as We Thought

#42

Post by mitchellpkt »

jhoelzel wrote: post #14
PoignardAzur wrote: post #10

Earlier quoted context omitted.

> but when i point it at a github repo with the github plugin enabled, it will answer the questions i have about the code pretty much on the nose. Holy crap, you can do that? I need to learn about ChatGPT plugins.

yes its in the "plugin store" and named "ask the code"

Note that at time of writing the “ask the code” plug-in does well with describing repo structure, but hallucinates file contents (I tested it on one of my own repos)

Re: ChatGPT Isn't as Good at Coding as We Thought

#43

Post by SanderNL »

namaria wrote: post #40
SanderNL wrote: post #33

Earlier quoted context omitted.

That’s an excellent observation. I struggled with this too and because I am fond of defective analogies this made me think of the meaning of a personal note to, say, a lover. Does it matter by whom or indeed what it was written? The experience of reading occurs solely in the recipient’s mind. Surely it does not affect him/her differently if said note was produced by a romantic slot machine. Before I meander towards m…

The difference is in the temporal dimension of the message. Generated text and code are simply statistically likely to convey enough meaning for the purpose at hand. That's all good and dandy until you think about the repercussions of communication. A person facing a problem and finding a solution encodes a message. This message ideally conveys context and purpose. The situation changes over time and we need to adapt…

Yes, the repercussions of this vacuousness are what interest me most. The underlying “systems” and “behaviors” that gave birth to the message are prior to any language model, but there, pre-language, is exactly where all changes happen. These changes then percolate to the top, so to speak, as language. I believe you captured this beautifully.

Then you get a bunch of humans that interpret this soulless message, but fail to comprehend the inherent emptiness sufficiently.

I’d say that’s not good, but I have no solution either.

Re: ChatGPT Isn't as Good at Coding as We Thought

#44

Post by namaria »

SanderNL wrote: post #43
namaria wrote: post #40

Earlier quoted context omitted.

The difference is in the temporal dimension of the message. Generated text and code are simply statistically likely to convey enough meaning for the purpose at hand. That's all good and dandy until you think about the repercussions of communication. A person facing a problem and finding a solution encodes a message. This message ideally conveys context and purpose. The situation changes over time and we need to adapt…

Yes, the repercussions of this vacuousness are what interest me most. The underlying “systems” and “behaviors” that gave birth to the message are prior to any language model, but there, pre-language, is exactly where all changes happen. These changes then percolate to the top, so to speak, as language. I believe you captured this beautifully. Then you get a bunch of humans that interpret this soulless message, but fa…

I see very little difference between letting LLMs create language that people and computer systems are expected to act upon and using oracles/'revealed' wisdom/sacred texts which dictate what we ought to want, decide and do. Letting inscrutable systems write the rules is just bad. We have 300 years of humanism building a base for our shared reasoning skills to enlighten the way and giving that up for the convenience of letting noise and chance guide us seems like going backwards.

Re: ChatGPT Isn't as Good at Coding as We Thought

#45

Post by jhoelzel »

mitchellpkt wrote: post #42
jhoelzel wrote: post #14

Earlier quoted context omitted.

yes its in the "plugin store" and named "ask the code"

Note that at time of writing the “ask the code” plug-in does well with describing repo structure, but hallucinates file contents (I tested it on one of my own repos)

maybe i have random successes or my questions are simpler than yours, but it works for me:

https://chat.openai.com/share/fbd14b6c-0ba0-473f-9e94-db97c6...

Re: ChatGPT Isn't as Good at Coding as We Thought

#46

Post by SanderNL »

wryanzimmerman wrote: post #38
SanderNL wrote: post #18

Earlier quoted context omitted.

The software indeed has to do what I do, which is understanding my environment and mentating solutions that are somehow appropriate for either fixing or alleviating any one of the uncountable challenges said environment faces. I cannot even describe what I am doing, only that relatively small parts of the end-result are encoded into symbols called code. This reminds me of what Bohr said to Oppenheimer - in the movie…

But the real question is whether or not an LLM can let someone who can hear the music (they’re an expert in the context, the project, and the business environment) but who can’t read or write the sheet music (can’t code) will be able to make the computer do what it needs to do well enough using the LLM as a sort of person to machine translator to eliminate the need for a person to listen to the subject matter expert…

Well, in that example the musician makes music and a machine could transcribe it to sheet music. I can see that working and maybe it already does.

What would be the equivalent of “making music” in this case? Talking haphazardly about your business?

I can see this working if something like “making music” is possible without knowledge of said music. Which in actual music is quite possible because it is an intuitive art. Programming.. less so, but I never say never.

Re: ChatGPT Isn't as Good at Coding as We Thought

#47

Post by selfhoster11 »

nwalizer wrote: post #29
selfhoster11 wrote: post #11

Earlier quoted context omitted.

The purpose of code is first and foremost to make a computer do things. Legibility is, strictly speaking, secondary.

I see you've never had to maintain code.

Code that doesn't run is just dead bytes. It's not useful for anything. Code that does run, even if impossible to comprehend without considerable research (like, say, DNA), is useful for something. You just cannot change its function.

I have maintained code, and even wrote some terrible stuff myself. All I'm saying is that once you strip all the lofty ideas about what code should be (which are all very good ideas!), then you are left with the very simple core idea: code is supposed to run and do stuff.

Re: ChatGPT Isn't as Good at Coding as We Thought

#48

Post by ChrisRR »

namaria wrote: post #41
ChrisRR wrote: post #7

Earlier quoted context omitted.

You can't understand why software that can do in a fraction of a section what a human would do in hours would be valuable?

You're describing automation. I'm talking about a very specific subset of it: automatically generating human or (human readable) language.

So if the job is to generate articles, technical reports, presentations, emails, marketing materials are the task, then generating human-like text is automating that task.
Post reply on HN