Using ChatGPT to generate a GPT project end-to-end • Hacker News Board

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

#61

Post by gwoolhurme » Sat, May 06, 2023, 2:15 PM UTC

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…

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.

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

#62

Post by ixaxaar » Sat, May 06, 2023, 2:22 PM UTC

sentrysapper wrote: post #55

Why the random forgetfulness?

I thought of that as a kind of dropout for memory, so that the network also learns to build resilience around what it stores. I was also unsure of how to manage the memory

- should I reset it every iteration? resulting in it behaving more like working memory maybe

- should I reset it every epoch? would that pollute the memory from previous iterations and what would happen if it got full?

- finally, why not maybe delete say 0.01% of the memory or maybe 1 cell per iteration randomly, this would imply the memory would not be that reliable as biological memory behaves and the neural net has to build resilience to use it effectively (by storing multiple copies of what is really useful (hyppocampal novelty detection type?)).

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

#63

Post by noman-land » Sat, May 06, 2023, 2:23 PM UTC

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.

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

#64

Post by muffles » Sat, May 06, 2023, 2:31 PM UTC

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…

Thats a great idea. I'm going to start doing this. For me it also seems GPT-4 just prints out slower. I find I can get most done with 3.5 and its faster to achieve what Im looking for. Then when I'm not satisfied with the 3.5 response I can clean it up and feed over into 4.

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

#65

Post by choeger » Sat, May 06, 2023, 2:31 PM UTC

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…

Calm down. It is a language model. People have figured out how to predict the next word for a given prefix. That's very cool and it will definitely have a significant impact on software. But it is not artificial intelligence.

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

#66

Post by hnlmorg » Sat, May 06, 2023, 2:34 PM UTC

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.

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

#67

Post by mlboss » Sat, May 06, 2023, 2:41 PM UTC

choeger wrote: post #65

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…

Calm down. It is a language model . People have figured out how to predict the next word for a given prefix. That's very cool and it will definitely have a significant impact on software. But it is not artificial intelligence.

What does it has to do that will qualify it as artificial intelligence ?

In my opinion, all the ingredients are there for artificial intelligence. Somebody just need to stitch everything up. It can understand text, reason about it, identity next steps, can write code to execute the steps, understand error messages and fix the code. That feels like AI.

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

#68

Post by gwoolhurme » Sat, May 06, 2023, 2:45 PM UTC

choeger wrote: post #65

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…

Calm down. It is a language model . People have figured out how to predict the next word for a given prefix. That's very cool and it will definitely have a significant impact on software. But it is not artificial intelligence.

God damn the down votes. I agree with your overall thesis I don’t personally know what intelligence means. However it’s just a tool even if it is AI or whatever you want to label it. It’s extremely cool and powerful too. It scares the shit out of me as well. However I think we are also taking the hype to 11/10 when it should be much lower out of 10 than that…

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

#69

Post by bonzini » Sat, May 06, 2023, 2:50 PM UTC

mlboss wrote: post #67

choeger wrote: post #65

Earlier quoted context omitted.

Calm down. It is a language model . People have figured out how to predict the next word for a given prefix. That's very cool and it will definitely have a significant impact on software. But it is not artificial intelligence.

What does it has to do that will qualify it as artificial intelligence ? In my opinion, all the ingredients are there for artificial intelligence. Somebody just need to stitch everything up. It can understand text, reason about it, identity next steps, can write code to execute the steps, understand error messages and fix the code. That feels like AI.

Be able to say "I don't know".

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

#70

Post by JKCalhoun » Sat, May 06, 2023, 2:52 PM UTC

mlboss wrote: post #67

choeger wrote: post #65

Earlier quoted context omitted.

Calm down. It is a language model . People have figured out how to predict the next word for a given prefix. That's very cool and it will definitely have a significant impact on software. But it is not artificial intelligence.

What does it has to do that will qualify it as artificial intelligence ? In my opinion, all the ingredients are there for artificial intelligence. Somebody just need to stitch everything up. It can understand text, reason about it, identity next steps, can write code to execute the steps, understand error messages and fix the code. That feels like AI.

We seem to keep moving the goal posts as to what is intelligence. I'm not sure is that ego? Or instead when we describe a thing and then see it, we say, “That is not what I meant at all; That is not it, at all.”