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

111–120 of 225 posts

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

#111

Post by leetbulb »

durdn wrote: post #90

I liked this metaphor: >It was more like handholding a fresh grad who had absorbed all of human knowledge but needed someone to tie various parts of that knowledge to create something useful.

This has definitely been my experience.

I experiment every so often with ChatGPT, usually having it create a simple multiplayer browser-based app with a server-side backend. The most recent being a collaborative pixel art app similar to /r/place.

Usually by the time ChatGPT generates something that actually works, after some guidance and generally minimal code edits (usually due to its context loss), I could've written a far more optimized version myself. Its capabilities are still extremely impressive nonetheless and I look forward to future iterations of this technology. Super nice tool to have for mundane code generation and it'll only get better.

Really wish I could use anything like this at work to generate tests... it's really good at that.

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

#112

Post by Yiin »

hnlmorg wrote: post #66
ineedasername wrote: post #54

This is not really the same, but may be interesting to some: I subscribe to ChatGPT plus for a month to check out GPT-4. The rate limits were cumbersome though and it can be easy to waste a prompt, so I started to bootstrap: I would explain my problem to 3.5 and ask it to suggest comprehensive prompts to use with 4 to maximize my limited quota. It worked very well. In the long years to come the most advance AIs may b…

I see this as an example of the reverse: AI is still stupid enough that it takes humans a degree of skill to craft a request which generates the desired output.

From what I've seen, the problem is not with the GPT models, but the people themselves. Almost everyday I get multiple unstructured, unclear and often without required context requests from people that I need to iterate back and forth with additional questions to get a clear view what they're trying to achieve. The only thing GPT is "stupid enough" is that it's not prompted to ask questions back to clarify the request.

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

#113

Post by olddustytrail »

noman-land wrote: post #63
pwillia7 wrote: post #41

Cool -- I did something similar with the goal: Imagine and simulate an instrument that doesn't exist and ended up with this -- it even created the assets or prompts for other AIs to make assets where it couldn't, including the model https://pwillia7.github.io/echosculpt3/

How is this an instrument? It looks like a rock.

The second request produced a roll.

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

#115

Post by samstave »

anotherpaulg wrote: post #114

I had chat gpt 3.5 build a small web app for me too. I have since been building some tooling for this sort of GPT-assisted programming. https://github.com/paul-gauthier/easy-chat

This deserves its own post, but that aside, please expand.

And take it from the perspective of ELI5 where one needs to basically set this up on a fresh install, what does it take?

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

#116

Post by anotherpaulg »

samstave wrote: post #115
anotherpaulg wrote: post #114

I had chat gpt 3.5 build a small web app for me too. I have since been building some tooling for this sort of GPT-assisted programming. https://github.com/paul-gauthier/easy-chat

This deserves its own post, but that aside, please expand. And take it from the perspective of ELI5 where one needs to basically set this up on a fresh install, what does it take?

The README in that repo tells the story of building that particular app. I recently got access to gpt-4, and the tooling I've built has become much more reliable. I will likely polish it up and put it onto GitHub sometime soon.

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

#117

Post by generic92034 »

jimbokun wrote: post #74
gwoolhurme wrote: post #61

Earlier quoted context omitted.

Could you explain in detail how that causes the singularity? I’m lost. I saw a cool tool used to make another cool tool. You saw the singularity. Where is this logic coming from? Why would terminal access which I’m fairly certain I’ve seen in autogpt, change much.

The cool tool makes another cool tool, which in turn makes another cool tool, faster and faster, until we really don't understand at all what the latest cool tool is doing. But it just keeps getting smarter/faster/more effective/whatever it's optimizing for. That's the basic definition of "the singularity".

What never was so clear to me in that vision is, how the version n actually makes sure the version n+1 is actually faster and better.

Initially there might be the easy option of using more tokens/memory/. But when that becomes impractical, how will the "dumber AI" select between x generated "smarter AIs"? How will it ensure that the newly generated versions are better at all (if there are no easily measurable parameters to be increased)?

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

#118

Post by bionhoward »

unshavedyak wrote: post #110
hnlmorg wrote: post #66

Earlier quoted context omitted.

I see this as an example of the reverse: AI is still stupid enough that it takes humans a degree of skill to craft a request which generates the desired output.

I don't know how true it is vs how much PR it is, but Khan Academy's use of LLMs was interesting in that they apparently craft a prompt from the AI itself. Ie a two step process where the AI generates the steps, and then the AI reasons about the result of the steps to attempt and judge the accuracy of the data. This was just a blurb from the Ted talk[1], but i'd be interested in seeing a slightly more in depth explan…

You can, I’m doing it right now

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

#119

Post by bionhoward »

c7b wrote: post #56

The technological singularity is approaching fast. It's pretty clear that, given terminal access and an appropriate outer loop, GPT models can iteratively create new GPT models (either by writing and executing Pyhton code, or later versions trained on LLM weights may even be able to output new weights directly). If the inner workings of the loop are sufficiently obfuscated (in the code-based version), it wouldn't nec…

The interpretability of LLMs comes in chain of thought. When a human explains a process, they talk through it. You don’t measure their neurons. The interpretability of neuron weights is a sub-symbolic red herring. Causal emergence says, the agent is what matters, not the individual synapse. Think like a manager with AI, not a cellular neurobiologist

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

#120

Post by rapiz »

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 also gave me a way to break down my requirements and feed them one at a time - as I was also acting as a code-reviewer for the generated output, and so this method was also easier for me to work with.

It takes a human who really knows the area to instruct ChatGPT and review the output, point out silly mistakes in the generated non-sense, and start next iteration. This kind of curated posts always cut off the most part of the conversations and the failed attempts, and then concatenate successful attempts with outputs of quality. Sure, it will be helpful as a super-IntelliSense. But not as helpful as the post suggested.

I've tried to do something like in the post, but I was quickly bored with waiting output, reviewing, all the iterations. One important aspect about programming is that reading code may not be easier than writing code. And in my case, it's more painful.

Post reply on HN