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

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

#221

Post by travisjungroth » Mon, May 08, 2023, 8:23 PM UTC

generic92034 wrote: post #219

travisjungroth wrote: post #207

Earlier quoted context omitted.

My point with the race analogy was you score it on the outcome (time) not a factor (horsepower). For your concern, just make the outcome broader. Someone will still say it’s not AGI as it does 100 different remote jobs, but just plan on ignoring them. Something that scares me is people don’t want to believe this is where we’re headed or it’s even possible. I say this because I think your concerns are easy enough to a…

The "easy" optimization targets I have mentioned (tokens/memory/etc.) seem to confuse you. Ignore them for the main point - how do you create good tests for a more advanced AI than you yourself are (or have control of)? For so many human fields of knowledge and ability it is already extremely hard to find meaningful tests to rank humans. No amount of letting an AI optimize on games with fixed and limited rules will a…

> how do you create good tests for a more advanced AI than you yourself are (or have control of)?

I think I answered that. You use more resources to create it than answer it. When creating it, you can have a team take lots of time, use all sorts of tools, etc. When taking it, you constrain time and tools. That’s the general pattern of how to make a question harder than you can answer.

There are also lots of trapdoor questions, especially in math. An overly simple example is factoring numbers.

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

#222

Post by generic92034 » Mon, May 08, 2023, 10:25 PM UTC

travisjungroth wrote: post #221

generic92034 wrote: post #219

Earlier quoted context omitted.

The "easy" optimization targets I have mentioned (tokens/memory/etc.) seem to confuse you. Ignore them for the main point - how do you create good tests for a more advanced AI than you yourself are (or have control of)? For so many human fields of knowledge and ability it is already extremely hard to find meaningful tests to rank humans. No amount of letting an AI optimize on games with fixed and limited rules will a…

> how do you create good tests for a more advanced AI than you yourself are (or have control of)? I think I answered that. You use more resources to create it than answer it. When creating it, you can have a team take lots of time, use all sorts of tools, etc. When taking it, you constrain time and tools. That’s the general pattern of how to make a question harder than you can answer. There are also lots of trapdoor…

I think that can only work with very small, incremental steps in intelligence, though. Will a ten year old human be able to create a meaningful test for an adult with high intelligence? No matter the resources you give the young one, they usually will not be able to.

There also might be thresholds, barriers, were small increments in intelligence are not possible. But that is speculative, I will admit.

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

#223

Post by travisjungroth » Tue, May 09, 2023, 1:29 AM UTC

generic92034 wrote: post #222

travisjungroth wrote: post #221

Earlier quoted context omitted.

> how do you create good tests for a more advanced AI than you yourself are (or have control of)? I think I answered that. You use more resources to create it than answer it. When creating it, you can have a team take lots of time, use all sorts of tools, etc. When taking it, you constrain time and tools. That’s the general pattern of how to make a question harder than you can answer. There are also lots of trapdoor…

I think that can only work with very small, incremental steps in intelligence, though. Will a ten year old human be able to create a meaningful test for an adult with high intelligence? No matter the resources you give the young one, they usually will not be able to. There also might be thresholds, barriers, were small increments in intelligence are not possible. But that is speculative, I will admit.

You don’t need big jumps. You have the previous version write the test for the next.

I’m not saying I’ve solved the path to AGI or anything. It’s just that this specific issue of “making a test harder than you can solve” has an answer.

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

#224

Post by stuckkeys » Tue, May 09, 2023, 1:41 AM UTC

ryanSrich wrote: post #220

stuckkeys wrote: post #153

Earlier quoted context omitted.

Request for a message cap increase. I think they go up to 100 but it depends on what you are doing.

Was there a form/email/person you contacted to do that? I can't find any such information online.

When you get the cap limit message. Click on the link it provides then fill out the form.

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

#225

Post by victor9000 » Wed, May 10, 2023, 3:27 AM UTC

dwallin wrote: post #216

edanm wrote: post #213

Earlier quoted context omitted.

What do you mean when you say this? Most people use hallucinate to mean "writes things that aren't true". It clearly and demonstrably is able to write at least some code that is valid and write some things that are true.

These models don't have a frame of reference to ground themselves in reality with, so they don't really have a base "truth". Everything is equally valid if it is likely. A human in a hallucinogenic state could hallucinate a lot of things that are true. The hallucination can feature real characters and places, and could happen to follow the normal rules of physics, but they are not guaranteed to do so. And since the i…

Precisely, the model is just regurgitating and pattern matching using a large enough training set where the outputs happen to look factual or logical. Meaning that we're just anthropomorphizing these concepts onto statical models, so it's not much different than Jesus Toast.