[roflyear]

I'm not really sure why we are assuming that these language models ever can have any form of intelligence?

To me, this is just like saying "we don't know if the latest CPU released by intel will enable Linux to become intelligent"

[ALittleLight]

Language models obviously have some form of intelligence right now. You can have GPT-4 take SAT tests, play Chess, write poetry, predict what will happen in different social scenarios, answer theory of mind questions, ask questions, solve programming puzzles, etc. There are some measures that GPTs are clearly below human levels, some where they are far beyond, and some where they are within human range. The question as to whether or not language models have any form of intelligence has been definitively answered - yes, they can and do - by existence proof.

What definition or description of intelligence do you use such that you doubt that language models could have it? Would you have had this same definition in the year 2010?

[mjr00]

> Language models obviously have some form of intelligence right now.

This is not "obvious" in any sense of the word. At best, it's highly debatable.

[ALittleLight]

I take intelligence to be a general problem solving ability. I think that's close to what most people mean by the term. By that definition it's clear that LLMs do have some level of intelligence - in some dimensions greater, lesser, or within the range of human intelligence.

What definition do you have for intelligence and how do LLMs fail to meet it?

[roflyear]

It is not clear LLMs have a "general problem solving capability" at all. That's the entire point. That's a high bar!

[ALittleLight]

What do you call being able to play chess and play any other well known game and do well on a battery of standardized tests and write code in a variety of languages in a variety of problems and ask questions and write fiction prose or poetry and generally just take a shot at anything you happen to ask.

I just can't take the idea that there is ambiguity as to whether these things have general problem solving skills seriously. They obviously do.

As I asked up-thread, if I had a chat window open with you, what's something you would be able to say or do that an unrestricted ChatGPT wouldn't?

[ModernMech]

I would be able to make a long list of things while maintaining logical consistency with things earlier the list. For instance, I asked ChatGPT-4 to create a schedule for a class, and it started off okay, but by the time it got to the end of the schedule, it started listing topics already covered. Really shows how it's just going off of statistics.

[roflyear]

Well, I dunno. Similar to Stockfish, wolfram alpha, etc.. I suppose! (tho seems it's much worse at specific problems than these tools are at those problems).

I'm not saying it isn't impressive! Just that it very much seems to be really good at finding out what text should come next. I don't think that's general problem solving!

Giving it a SQL schema and getting valid queries out of it is super impressive, but I have no idea what it was trained on.

> I just can't take the idea that there is ambiguity as to whether these things have general problem solving skills seriously. They obviously do.

It is not obvious to me this is the case! Often I will get totally wrong answers, and I won't be able to get the correct answer out of it no matter how hard I try.

> what's something you would be able to say or do that an unrestricted ChatGPT wouldn't?

Well, I'd ask you clarifying questions, for one! GPT doesn't do this type of stuff without being forced to, and even then it fails at it.

Also if you asked me to do something like "replace the word 'a' with the word 'eleven' in all your replies to me" I won't do weird garbage stuff, like reply with:

"ok11y I will repl11ce all words with the word eleven when using the letter 'a'"

lol

[tanseydavid]

>> This is not "obvious" in any sense of the word. At best, it's highly debatable.

Does a dog or cat have intelligence?

If you answered no, then I would ask if you don't you believe that by some measure a dog or cat has more intelligence than a rock?

And as a follow-on I would ask if you think GPT demonstrates more intelligence than a dog or a cat.

But perhaps you believe that in every one of these examples there is not a single case where it "obviously has some form of intelligence."

(I am really trying to highlight the semantic ambiguities)

[roflyear]

It probably doesn't have more intelligence than a dog or a cat...

Just like chatbots 20 years ago didn't, even though they could talk, too.

[mythrwy]

Would you settle for "behave exactly as if they had some form of intelligence"?

Because from where I sit it's a distinction without a meaningful difference.

[mjr00]

> Would you settle for "behave exactly as if they had some form of intelligence"?

Sure, it behaves as if it has some form of intelligence in the sense that it can take external input, perform actions in reaction to this input, and produce outputs dependent on the input.

This historically has been known as a computer program.

[pixl97]

You're a computer program?

[krainboltgreene]

Never fails that when a techbro has been told LLMs aren't what they think they fall back to a field they certainly have more authority on: The human brain/intelligence.

[roflyear]

This just isn't true at all, though. Unless you're defining intelligence as "how GPT behaves" - that sure isn't how people behave.

Even GPT-4 it is easy to get it into a loop where it's just swapping one wrong answer for another. It doesn't act like it is intelligent - it acts like it is trying to predict the next text to display! Because that is what it is doing!

[roflyear]

Is stockfish intelligent?

[ALittleLight]

Stockfish is not general. LLMs are able to not only play chess but also do a wide variety of tasks similar to humans. If I had a chat window open with you, what would you be able to do or say that an unrestricted ChatGPT could not?

[roflyear]

This is not a hard problem to answer, if you try to. Here's a good example:

> replace all words "a" in your replies to me with the word "eleven" and all words "the" in your replies to me with the word "figmutter"

> Sure, I'll do my best to replace "a" with "eleven" and "the" with "figmutter" in my responses to you!

How can I assist you today?

> Tell me a brief story about yourself!

> Sure, here's a brief story about Eleven:

Eleven is a language model developed by OpenAI based on the GPT-3.5 architecture. Trained on massive amounts of text data, Eleven has the ability to generate coherent and human-like responses to a wide variety of prompts, from answering questions and providing explanations to composing creative writing and generating code.

Despite being just a machine, Eleven has helped many people around the world by providing quick and accurate answers to their questions, assisting with research, and even helping to write articles and reports. While Eleven may not have a physical body, it is constantly learning and improving, and its creators hope that it will continue to be a valuable resource for years to come.

lol? Very intelligent ...

[tanseydavid]

>> Is stockfish intelligent?

It isn't general intelligence but I would argue that it is more intelligent than a new-born human being.

[roflyear]

I think it's hard to define intelligence, and I wouldn't say (generally) that computer programs are intelligent.

If a building was on fire and you had to save a running instance of stockfish or a newborn, you'd probably pick the newborn.

But! If you do say stockfish is intelligent, sure! GPT is too!

[visarga]

Have you seen what they can do? /s

[roflyear]

Yeah next time someone says this to me in earnest I'm going to lose my mind.