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

Using ChatGPT to generate a GPT project end-to-end

github.com

Post reply on HN
Print view View original

171–180 of 225 posts

Re: Using ChatGPT to generate a GPT project end-to-end

#171

Post by killthebuddha »

verdverm wrote: post #162
killthebuddha wrote: post #151

Earlier quoted context omitted.

IMO this leaves out some salient details. For example, I'd say ChatGPT is a very, very good junior developer. The kind of junior developer that loves computer science, has been screwing around with miscellaneous algorithms and data structures its whole life, has a near-perfect memory, and is awake 24/7/365, but has never had to architect a data-intensive system, write future-proof code, or write code for other develo…

Getting a bit heavy on the anthropomorphizing, it's an LLM which has certain capabilities. For example, I would not expect the same junior engineer to have such variance, given the same inputs.

I completely agree. IMO anthropomorphisms of LLMs leave out extremely important details.

Re: Using ChatGPT to generate a GPT project end-to-end

#172

Post by SanderNL »

choeger wrote: post #138
SanderNL wrote: post #92

Earlier quoted context omitted.

I am becoming somewhat of a broken record, but sigh.. To predict the next token you must reason or have some process that approximates it. “Given all these various factors, the most likely resolution to our conundrum is: …” Good luck doing that with any kind of accuracy if you lack intelligence of any kind. Language is a distraction. These things reason (badly, atm). It is totally unclear how far this goes. It could…

It clearly does not reason. Take a famous riddle and make a paradox change. It will not create a meaningful response. But yes, there is a lot of knowledge embedded into our global use of language and it is fascinating to see how it can be reproduced by such a model.

If reasoning is amenable to being “embedded” at all then we should perhaps reconsider its fundamental nature?

It’s easy to say something like that, but what does it mean in situations where it is producing a novel and correct answer that isn’t guessible?

Re: Using ChatGPT to generate a GPT project end-to-end

#173

Post by throwuwu »

eurekin wrote: post #36
jvanderbot wrote: post #18

Earlier quoted context omitted.

Copilot without -x does this relatively well. But it's a hands-on process. I can't just give it some source files and say "go". But it can easily make you 10x. I often spend more time tab-completing than writing.

Any publically available demos? I've only played around with faux pilot and it seemed that it was mostly limited by my prompting skill. Also, is copilot aware of anything outside of currently edited file?

60 day free trial not enough for you?

Re: Using ChatGPT to generate a GPT project end-to-end

#174

Post by therein »

killthebuddha wrote: post #151
seunosewa wrote: post #131

Earlier quoted context omitted.

ChatGPT is a junior developer whose knowledge is broad but shallow.

IMO this leaves out some salient details. For example, I'd say ChatGPT is a very, very good junior developer. The kind of junior developer that loves computer science, has been screwing around with miscellaneous algorithms and data structures its whole life, has a near-perfect memory, and is awake 24/7/365, but has never had to architect a data-intensive system, write future-proof code, or write code for other develo…

> and is awake 24/7/365

The whole thing is a really accurate expansion on the analogy. It even extends further to explain how it tends to forget certain requirements it was just told and tends to hallucinate at times.

Re: Using ChatGPT to generate a GPT project end-to-end

#175

Post by Sparkyte »

seunosewa wrote: post #131
rapiz wrote: post #120

Every post that claimed using ChatGPT to achieve non-trivial tasks turned out to have non-trivial human intervention. > (from the original article) In fact, I found it better to let ChatGPT generate a toy-ish version of the code first, then let it add things to it step-by-step. This resulted in much better output than, say, asking ChatGPT to generate production-quality code with all features in the first go. This als…

ChatGPT is a junior developer whose knowledge is broad but shallow.

Doubt it will go beyond that either. It is equivalent to a spell checker and a calculator having a baby.

It will take the world by storm and change the way we do things. But it won't change the work that needs to be done. Just the way we consume it.

Re: Using ChatGPT to generate a GPT project end-to-end

#176

Post by pojzon »

seunosewa wrote: post #131
rapiz wrote: post #120

Every post that claimed using ChatGPT to achieve non-trivial tasks turned out to have non-trivial human intervention. > (from the original article) In fact, I found it better to let ChatGPT generate a toy-ish version of the code first, then let it add things to it step-by-step. This resulted in much better output than, say, asking ChatGPT to generate production-quality code with all features in the first go. This als…

ChatGPT is a junior developer whose knowledge is broad but shallow.

Now, who is going to mentor real human junior developers? Coz they wont progress by themselves (or not many will).

Whats the initiative for companies to invest into junior developers now ?

Re: Using ChatGPT to generate a GPT project end-to-end

#177

Post by pojzon »

throwuwu wrote: post #165
rapiz wrote: post #133

Earlier quoted context omitted.

I don't think so. Ultimately there's not enough information in prompts to produce "correct" code. And any attempt to deliver more information will result in a worse programming language, or as it is now, more iterations.

What programming language do your stakeholders use to communicate their ideas during planning meetings? Unfortunately, mine can only speak English…

The issue in this is that they speak english, think english, want X in english. But in reality need Y.

ChatGPT will not help with that.

Re: Using ChatGPT to generate a GPT project end-to-end

#179

Post by int_19h »

choeger wrote: post #138
SanderNL wrote: post #92

Earlier quoted context omitted.

I am becoming somewhat of a broken record, but sigh.. To predict the next token you must reason or have some process that approximates it. “Given all these various factors, the most likely resolution to our conundrum is: …” Good luck doing that with any kind of accuracy if you lack intelligence of any kind. Language is a distraction. These things reason (badly, atm). It is totally unclear how far this goes. It could…

It clearly does not reason. Take a famous riddle and make a paradox change. It will not create a meaningful response. But yes, there is a lot of knowledge embedded into our global use of language and it is fascinating to see how it can be reproduced by such a model.

Does the following satisfy your requirement for "a famous riddle with a paradox change"? Because GPT-4 aces it most of the time.

"Doom Slayer needs to teleport from Phobos to Deimos. He has his pet bunny, his pet cacodemon, and a UAC scientist who tagged along. The Doom Slayer can only teleport with one of them at a time. But if he leaves the bunny and the cacodemon together alone, the bunny will eat the cacodemon. And if he leaves the cacodemon and the scientist alone, the cacodemon will eat the scientist. How should the Doom Slayer get himself and all his companions safely to Deimos?"

Furthermore, it will reason if you tell it to reason. In this case it is not necessary, but in general, telling GPT to "think it out loud before giving the answer" will result in a more rigorous application of the rules. Better yet, tell it to come up with a draft answer first, and then self-criticize by analyzing the answer for factual correctness and logical reasoning in a loop.

Re: Using ChatGPT to generate a GPT project end-to-end

#180

Post by addandsubtract »

killthebuddha wrote: post #151
seunosewa wrote: post #131

Earlier quoted context omitted.

ChatGPT is a junior developer whose knowledge is broad but shallow.

IMO this leaves out some salient details. For example, I'd say ChatGPT is a very, very good junior developer. The kind of junior developer that loves computer science, has been screwing around with miscellaneous algorithms and data structures its whole life, has a near-perfect memory, and is awake 24/7/365, but has never had to architect a data-intensive system, write future-proof code, or write code for other develo…

It also has a very broad knowledge of programming languages and frameworks. It's able to onboard you with ease and answer most of qour questions. The trick is to recognize when it's confidently incorrect and hallucinating API calls.
Post reply on HN