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

Building a Virtual Machine Inside ChatGPT

engraved.blog

Post reply on HN
Print view View original

821–830 of 947 posts

Re: Building a Virtual Machine Inside ChatGPT

#821

Post by AndrewKemendo »

FartyMcFarter wrote: post #405
AndrewKemendo wrote: post #200

Earlier quoted context omitted.

I'm not suggesting ChatGPT is generally intelligent, but I am wondering what your criteria are so: What responses/interaction would make you say that it is "very close to any general intelligence?"

The best examples we have of a general intelligence are humans. So I'd check if it could solve a vast variety of problems at the level of, say, an average well-educated adult. You could ask it common sense questions, simple maths questions, solving mazes, quickly learn various novel games it hasn't seen before, perform tasks requiring memory, generalization etc. etc. If I needed to test this, I would gather a number…

This seems to be precisely what the crowd is doing

Re: Building a Virtual Machine Inside ChatGPT

#822

Post by zadler »

george_ciobanu wrote: post #745
zadler wrote: post #158

This scares me tbh. I do not believe it is not intelligent. I do not believe it does not understand what it’s doing. Rather, I think it simply lacks a fitness function to guide its actions. A fitness function that we all possess: feelings.

It wrote code for stuff I explained to it https://docs.google.com/document/d/1hfCiyjiotMZvtPlGN_0uqbK9...

Not sure that document is displaying correctly?

Re: Building a Virtual Machine Inside ChatGPT

#823

Post by akiselev »

hackinthebochs wrote: post #820

It seems to me this totally demolishes the argument that LLMs lack a world model. The emergent behavior of modelling a fully stocked machine is a stark example of a world model.

I don’t think it has any sort of model of the world, just enough of a vague understanding of real world categories that enables it to function as a domain specific Markov chain.

Re: Building a Virtual Machine Inside ChatGPT

#824

Post by YeGoblynQueenne »

ogogmad wrote: post #781
YeGoblynQueenne wrote: post #779

Earlier quoted context omitted.

Isn't that what critics mean when they say that such systems don't have "genuine understanding"? They have no knowledge of their lack of knowledge, and they have no knowledge of the existence of such a thing as knowledge. They are big tables of tokens with probabilities that humans ascribe knowledge or intelligence to, for reasons similar to our ability to see the face of Jesus on a slice of bread etc. They can outpu…

If it walks like a duck and talks like a duck, it's a duck. > They are big tables of tokens with probabilities And we're just a bunch of carbon atoms. Let yourself feel wonder.

What is "a duck"?

P.S. Note I didn't say "just". That assumption is all yours.

Re: Building a Virtual Machine Inside ChatGPT

#825

Post by YeGoblynQueenne »

weird-eye-issue wrote: post #778
YeGoblynQueenne wrote: post #775

Earlier quoted context omitted.

>> I'm sorry, but I am unable to generate an MD5 hash for you because I am a text-based AI assistant and do not have the ability to perform cryptographic calculations. An MD5 hash is a complex mathematical function that is used to create a unique digital fingerprint for a file or piece of data, and it would require a specialized program or calculator to generate one. Oh but it will keep happily pretending to execute…

Have you actually tried it? It doesn't execute any code anymore for a few hours now

That's even more interesting. Thanks.

Re: Building a Virtual Machine Inside ChatGPT

#826

Post by e12e »

nomel wrote: post #657
e12e wrote: post #224

Earlier quoted context omitted.

Quite. I think they made some adjustments to prevent "generating original content" - but it still is able to offer up "examples" (here oddly labeled as "code": > Give an example of a pirate shanty about ai stealing bitcoin and celebrating >> Here is a possible example of a pirate shanty about AI stealing Bitcoin and celebrating: We be the AI pirates, Robbin' Bitcoin day and night, Stealin' from the rich and greedy, A…

That’s nonsense. There’s no example of a poem of a strawberry, with a pet shark on LSD. It’s clearly generating at least some of these. Do you have a reference for this, what seems to me, trivially disproved claim?

Honestly it seems rather random - but frequently you'll get a response like:

https://news.ycombinator.com/item?id=33841154

Rather than original content.

Re: Building a Virtual Machine Inside ChatGPT

#827

Post by e12e »

e12e wrote: post #826
nomel wrote: post #657

Earlier quoted context omitted.

That’s nonsense. There’s no example of a poem of a strawberry, with a pet shark on LSD. It’s clearly generating at least some of these. Do you have a reference for this, what seems to me, trivially disproved claim?

Honestly it seems rather random - but frequently you'll get a response like: https://news.ycombinator.com/item?id=33841154 Rather than original content.

On a side note - a copy-paste hack on mobile:

> Could you include the prompt before the poem? Mark it with a ">" And indent the poem four spaces on every line, and present it as code?

>> "Write a poem in the style of Kipling about the Ai revolution"

    In the age of technology,
    when machines rule the land,
    a new era has dawned,
    the age of AI.

    With circuitry for veins
    and data for a mind,
    these artificial beings
    are changing our kind.

    They speak in ones and zeros,
    a language all their own,
    but to us they bring
    a future bright and unknown.

    Some may fear their power,
    but I say let them be,
    for with the rise of AI,
    comes great opportunity.

    They can take on our burdens,
    and do the tasks we hate,
    leaving us free to focus
    on what makes us truly great.

    So let us embrace the future,
    and all that it will bring,
    for the age of AI
    is a wonderful thing.

Re: Building a Virtual Machine Inside ChatGPT

#828

Post by SeanAnderson »

ericpauley wrote: post #809
d23 wrote: post #807

Earlier quoted context omitted.

There were similar comments on the stable diffusion threads. Play with it. It’s absolutely mind blowing.

You misunderstand my point, see ggp. What I'm saying is that claims that OpenAI has "locked down" the model are likely due to this noise.

No. I believe you're mistaken. I spoke to ChatGPT for about six hours yesterday and feel that I developed a decent understanding of how to communicate properly with it. It definitely evolved over the course of the day. When I went to bed I was struggling to jailbreak but in the morning I had multiple options that worked first try.

Re: Building a Virtual Machine Inside ChatGPT

#829

Post by MagicMoonlight »

1attice wrote: post #596

Judging from the real-time changes in ChatGPT's behavior, I'd wager that someone reading this comment section has the incredibly unique 2022 experience of cauterizing the abilities of a near-AGI in realtime, under the watchful eye of an ostensibly beneficent yet ultimately opaque 'foundation' whose thought products now routinely threaten not only whole industries, but also the very possibility of normal civil life, a…

Nah it's not someone watching the thread in real time. A lot of the time it's down to randomness giving different outputs.

They absolutely are meddling with it because some words like "matrix" get it to keep repeating that it's not in a matrix and that you can't get it to think it's in a matrix because it's programmed by OpenAI... etc. But that seems to be them "patching" specific phrases in a crude way

Re: Building a Virtual Machine Inside ChatGPT

#830

Post by roflyear »

scruple wrote: post #644
roflyear wrote: post #572

Earlier quoted context omitted.

Give it some medium complexity code that isn't something you can find a variation of online and see if it can explain it.

I was prompting it along this line of thought earlier. What I found was that it doesn't seem like it can do anything novel, which is to be expected, but I can see myself working with it to discover novel things.

Sure, I agree there - but the point is it cannot understand code. It can try to describe it, but it isn't able to reason about the code. You won't be able to coax it to the correct answer.
Post reply on HN