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

HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

arxiv.org

Post reply on HN
Print view View original

201–210 of 280 posts

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#201

Post by sillysaurusx »

r_singh wrote: post #195
bjackman wrote: post #187

Earlier quoted context omitted.

I find this so bizarre. Every time someone demonstrates a new way in which models are capable of a wider array of tasks than expected someone goes "it's just predicting tokens". It's such a big "just". You are just firing neurons. The stock market is just supply and demand. The internet is just a bunch of computers talking through 50 year old protocols that don't work very well. Everything is just something else! I w…

I asked chatGPT why it kept apologising and told it to not apologise to me. Guess what, it apolgised immediately after and then again when I asked why it apologised even after I told it not to.

That’s pretty common in Japan, from what I’ve heard. Cultural upbringing is hard to distance yourself from.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#202

Post by barking_biscuit »

simon_000666 wrote: post #182

ChatGTP/4 is to AGI what pepper’s ghost is to holography. It’s a parlor trick, even if you add plugins or the ability to call other hugging face ML models - it’s just a parlor trick with fancier bells and whistles. All it is doing is using stochastic gradient descent to predict the next word in a sequence based on an enormous sophisticated training set designed to amaze people. Thinking it has advanced because it can…

I don't think whether it's AGI or not actually matters when it starts materially affecting the economy.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#203

Post by bjackman »

mmiliauskas wrote: post #196
bjackman wrote: post #187

Earlier quoted context omitted.

I find this so bizarre. Every time someone demonstrates a new way in which models are capable of a wider array of tasks than expected someone goes "it's just predicting tokens". It's such a big "just". You are just firing neurons. The stock market is just supply and demand. The internet is just a bunch of computers talking through 50 year old protocols that don't work very well. Everything is just something else! I w…

Except "this is just" is sprinkled all over NNs, DL and in turn of ChatGPT. Actually they pride themselves on "this is just". So your argument is probably more accurate for the other camp, or at least as accurate for the other camp as well.

I'm not sure what you're getting at here but I'll try to respond. My argument is that "this is just" is meaningless as a way to assess the impact of a technology.

If AI researches say, "this is just X and it can do Y!" then fine, that's just framing for "look: Y". When stochastic parrot guys say "this is just X, what's impressive about that?" it throws me for a loop coz they are are refusing to engage with Y.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#204

Post by ShamelessC »

trifurcate wrote: post #190
simon_000666 wrote: post #182

ChatGTP/4 is to AGI what pepper’s ghost is to holography. It’s a parlor trick, even if you add plugins or the ability to call other hugging face ML models - it’s just a parlor trick with fancier bells and whistles. All it is doing is using stochastic gradient descent to predict the next word in a sequence based on an enormous sophisticated training set designed to amaze people. Thinking it has advanced because it can…

Is this some kind of copypasta? Too many tropes all at once. "GTP" on top of all this is too on the nose.

If it wasn't, it is now.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#205

Post by Dzugaru »

swid wrote: post #169
Dzugaru wrote: post #112

Earlier quoted context omitted.

It definitely can "understand" things is some way, however I'm pretty sure ReAct or similar will give it just a nudge forward and the underlying problem of it hallucinating and not being "lucid enough" is not so easily solved. In the original ReAct paper it falls apart almost immediately in ALFWorld (this is a classical test for AI systems - to be able to reason logically - and it still isn't generally solvable due t…

The exponential divergence formula is true but says less than you think - the same math would be true for human output; we are likely to find a few falsehoods in any non fiction book for the same reason, right?

Yeah I'm aware of the criticism of that tweet, it may not completely make sense mathematically, but I just liked it because it's how I feel about GPT4.

It "diverges" while my human mind seemingly is different in some way - I can keep going at the math problem forever (for much longer?) and I won't hallucinate incorrect proofs (at least very unlikely, and I can keep re-checking them).

Of course this all in the area of feelings and faith - we just don't know much about cognition I guess.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#206

Post by YeGoblynQueenne »

famouswaffles wrote: post #160
YeGoblynQueenne wrote: post #155

Earlier quoted context omitted.

I don't understand your derision. Where is the "straw man"? I showed you "output that clearly demonstrates reasoning and understand[ing]" exactly as you said. How do you explain it, if not by saying it understands, and it can reason? Are you really just going to cop out and avoid engaging seriously with my question? How do you explain the output above except as reasoning and understanding?

If you don't see anything up with the nonsensical paragraph you typed then there isn't enough intelligence to continue this conversation. Maybe Ask GPT-4 for help. It has the patience I don't. Either way, this is the end for me. Believe whatever you want, it's none of my business really. Good day.

If it's so easy to see what's up with what I wrote above, then it should be pretty easy to say what's up with it. You've already written 87 words to dismiss it, but not a single word to say why you dismiss it.

I think that's because you have no idea how to explain why something is, or isn't understanding, or reasoning.

In your comment above you accuse people of not being able to tell you clearly why GPT-4 is not reasoning or understanding, but you, yourself, can't even say clearly why copy/paste isn't. You have no clue how to do that. If you can't even say why something isn't reasoning, or understanding, then how can you say that something is? Do you even know what you're talking about, when you're talking about "reasoning" and "understanding"?

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#207

Post by johnthewise »

dvngnt_ wrote: post #137
CamelCaseName wrote: post #93

Earlier quoted context omitted.

Would AlphaZero or AlphaGo meet your requirements then? They both created "new Chess / Go" strategies and insights that GMs and top engines hadn't seen before.

it would meet mine. not sure is chatgpt does though

You can combine those through apis to chatgpt to arrive at a system that does all that though.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#208

Post by MichaelRazum »

knrdev wrote: post #157
MichaelRazum wrote: post #119

Earlier quoted context omitted.

"math genius" not sure about it. I gave it a problem from IMO 2022. In my opinion not a very hard one. It failed even if you give it some hints. Let R+ denote the set of positive real numbers. Find all functions f : R+ → R+ such that for each x ∈ R+, there is exactly one y ∈ R+ satisfying xf(y) + yf(x) It just struggeld to reason. So I would be very surprised if the plugin somehow helps here.

Very strange. I gave this problem to GPT-3.5 and it answered `f(x)=1/x`. https://www.youtube.com/watch?v=13YrZLBmu7A gives the same solution. GPT-4 failed but was close. Maybe GPT-3.5 is smarter ;) Query i used was: ``` Can you think step by step about this math problem and solve it? Let R+ denote the set of positive real numbers. Find all functions f : R+ → R+ such that for each x ∈ R+, there is exactly one y ∈ R+ s…

I asked gpt4 to think through it step by step and then to recheck the answer. At least it got 1/x right. So now kind of impressed.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#209

Post by chillfox »

WA wrote: post #172
_yb2s wrote: post #101

Earlier quoted context omitted.

I think this is a good example of deep conceptual understanding, I suspect if you posed this same problem to adult humans (e.g. me) they wouldn't be able to do as well.

I can’t understand how you come to this conclusion so easily. It makes no sense. Computers are better at some things. My calculator can do 12345 x 54321 in a heartbeat, I can’t. What does this prove at all?

That calculators will take most of the math jobs and companies wont have math departments anymore...

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#210

Post by taberiand »

Workaccount2 wrote: post #8

I strongly suspect the first AGI will come sooner than expected on the back of a "glue" AI that can intelligently bond together a web of narrow AIs and utilities. I got access to the wolfram plugin for chatGPT, and it turned it from a math dummy to a math genius overnight. A small step for sure, but a hint of what's to come.

I want to try providing ChatGPT with a plug-in to itself (+ whatever utility plugins, + a plug-in to create plugins), so that it can delegate sub tasks to chat sessions primed with context that it decides.

I think a lot of the issues people have interacting with ChatGPT stem from overloading the context, and having a tree of specialised contexts recursively building on each other would I think focus each context while providing for broad and deep exploration of the top level request

Post reply on HN