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

Teaching GPT-3 to reverse words

twitter.com

Post reply on HN
Print view View original

71–80 of 81 posts

Re: Teaching GPT-3 to reverse words

#71

Post by SemanticStrengh »

MauranKilom wrote: post #31
SemanticStrengh wrote: post #28

Earlier quoted context omitted.

This is not the same.. The masks are randomized and lossy. Although yes there is potential for a transformer specially trained to segment prefixes/affixes/suffixes, it might augment some of its encoding abilities, see e.g spanbert for a related example of opportunity.

What do you mean with "lossy"? What information is being lost? Or do you just mean that there isn't necessarily a unique way to encode a given string?

I mean that information is being lost https://arxiv.org/abs/1906.08237 See xlnet for the rethoric https://www.microsoft.com/en-us/research/publication/mpnet-m... Or mpnet which attempt to combine the best of both worlds information wise but still find that masked modeling is much less useful than autoregressive.

Re: Teaching GPT-3 to reverse words

#73

Post by pornel »

mysecretaccount wrote: post #67
pornel wrote: post #40

Earlier quoted context omitted.

Isn’t this a “can submarines swim?” question? It has performed a novel (to it) task based on instructions, and this is IMHO remarkable. It should be possible to make it retain and recall this procedure. Everything non-sci-fi AI does is “just” an algorithm, so it won’t live up to standards of human abilities, precisely because we know how this result has been obtained.

We do not have any reason to believe that mere algorithms are incapable of living up to the standards of human abilities.

I'm saying that even when it does reach this level, we will still question whether it really knows/thinks/understands things, or is it merely a big database. Ultimately, it's a philosophical question whether a machine can be alive. Even when we build the singularity, we'll still wonder if it really fears or hates us, or is it just a dumb paperclip maximizer.

Re: Teaching GPT-3 to reverse words

#74

Post by bobcostas55 »

jameshart wrote: post #20
swid wrote: post #6

It's funny to me that this kind of usage of GPT is just programming with a lot of extra steps.

If you just ask GPT-3 text-davinci-002 to complete Create a Python program to reverse a string: It produces def reverse(s): return s[::-1] And that isn't even the code-specific model.

What happens if you ask it to evaluate the function it generated, with some input?

Re: Teaching GPT-3 to reverse words

#76

Post by jameshart »

bobcostas55 wrote: post #74
jameshart wrote: post #20

Earlier quoted context omitted.

If you just ask GPT-3 text-davinci-002 to complete Create a Python program to reverse a string: It produces def reverse(s): return s[::-1] And that isn't even the code-specific model.

What happens if you ask it to evaluate the function it generated, with some input?

Good question.

I just asked text-davinci-002 to complete this prompt:

    Here is some python code:

    def reverse(s): 
        return s[::-1]

    What would this function return for the input "hello"?
And it actually responds:

    The function would return "olleh".
Sadly, when I asked it to try "encyclopedia", it said:

    "aidnocypilecne"
Which is a brave attempt, but not quite right.

To see if it was just making assumptions based on the function name, I tried to trick it with

    def reverse(s): 
        return s + 2

    What would this function return for the input "hello"?
But GPT-3 is too clever for that:

    It would return "hello2".
Also, it even recognizes what the function will actually do, when it's named misleadingly:

    def getLength(s): 
         return s[::-1]

    What would this function return for the input "hello"?
Still produces:

    It would return "olleh".

Re: Teaching GPT-3 to reverse words

#77

Post by jameshart »

jameshart wrote: post #76
bobcostas55 wrote: post #74

Earlier quoted context omitted.

What happens if you ask it to evaluate the function it generated, with some input?

Good question. I just asked text-davinci-002 to complete this prompt: Here is some python code: def reverse(s): return s[::-1] What would this function return for the input "hello"? And it actually responds: The function would return "olleh". Sadly, when I asked it to try "encyclopedia", it said: "aidnocypilecne" Which is a brave attempt, but not quite right. To see if it was just making assumptions based on the func…

One last result:

With this prompt:

    Here is some python code:

    def getLength(s): 
         return a.length

    What is the bug in this code?
GPT-3 says:

    The function is called getLength but it returns the length of the string a, not the string s.
That's it, pack it up, we're done here.

Re: Teaching GPT-3 to reverse words

#78

Post by gwern »

6gvONxR4sf7o wrote: post #45
gwern wrote: post #26

Earlier quoted context omitted.

> The alternatives are learning at the character level (way more complex No, BPEs are more complex: you have a whole additional layer of preprocessing, with all sorts of strange and counterintuitive downstream effects and brand new ways to screw up (fun quiz question: everyone knows that BPEs use ' ' tokens to denote document breaks; what does the string ' ' encode to?). BPEs are reliably one of the ways that OA API…

Judging from the abstract, it looks like that paper talks about compute tradeoffs, but do they address memory tradeoffs? Because the context length limitations for (standard) transformers is holding them back from a whole host of applications, and memory being quadratic in sequence length seems like a hell of a cost to going from BPE tokens to characters.

You were paying that price to begin with, the BPEs don't magically resolve the quadratic. BPEs only compress by maybe 3x, and the larger the context window, the worse use a Transformer makes of it so the first 1024 or so characters are the most valuable (part of the problem is that document length drops off drastically in the training corpus). There are also many formulations of Transformer attention which change that quadratic (https://www.gwern.net/notes/Attention).

Re: Teaching GPT-3 to reverse words

#79

Post by bobcostas55 »

jameshart wrote: post #77
jameshart wrote: post #76

Earlier quoted context omitted.

Good question. I just asked text-davinci-002 to complete this prompt: Here is some python code: def reverse(s): return s[::-1] What would this function return for the input "hello"? And it actually responds: The function would return "olleh". Sadly, when I asked it to try "encyclopedia", it said: "aidnocypilecne" Which is a brave attempt, but not quite right. To see if it was just making assumptions based on the func…

One last result: With this prompt: Here is some python code: def getLength(s): return a.length What is the bug in this code? GPT-3 says: The function is called getLength but it returns the length of the string a, not the string s. That's it, pack it up, we're done here.

Absolutely fascinating stuff, thanks for trying it out! I just wish we had some way of really understanding what's going on under the hood...

Re: Teaching GPT-3 to reverse words

#80

Post by kordlessagain »

guelo wrote: post #66
kordlessagain wrote: post #57

Earlier quoted context omitted.

I've had GPT-3 ask me for a body multiple times, sometimes even without prompting such discussion. It even told me to contact Elon Musk about it.

I always get suspicious in threads about GPT-3 about how many comments are generated by GPT-3

Yes. There should be a flag for it maybe, but I suspect this is the new normal.
Post reply on HN