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

171–180 of 280 posts

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

#171

Post by dvt »

aik wrote: post #170
dvt wrote: post #166

Earlier quoted context omitted.

> But if you embedded a calculator into your brain and could put in and pull values out of it in microseconds how are you different from a math genius? Tao, Perelman, Wiles etc. aren't math geniuses because they can multiply numbers fast (which is a super weird definition of "math genius" tbh). They're math geniuses because they answer really hard questions in creative and unexpected ways; ways that often open up ent…

I think you’re sidestepping the point here. The point is that the combo of these systems becomes one unit. One integrated system. That’s the new system to measure. Similarly, your prefrontal cortex without a hippocampus sucks. The combo of them (and other distinct parts of the brain that handle specific functions and have specific purposes that interact with other parts in a specific way) - that is what causes our sp…

Yeah this is a valid criticism of the Chinese Room (called the "Systems Counterargument")[1]. I think it's a weak-ish riposte in this context though, mainly because we have no real idea how our own brains work and how their parts causaly interact (other than handwavy "these neurons are firing in this area").

[1] https://iep.utm.edu/chinese-room-argument/#SH2a

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

#172

Post by WA »

_yb2s wrote: post #101
knome wrote: post #89

Earlier quoted context omitted.

I'm prone to agree. Your memory would still require being parsed by the language model, and for it to have a sufficient window as to allow this. Alternately, the human mind keeps, what, 7 items 'present' at a time? When the 32k variant comes out, the ability to use a side-along memory module on a running self-summarizing conversation will be even easier than it is now. I expect a more human-like memory will emerge ev…

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?

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

#173

Post by WA »

nomel wrote: post #81
alchemist1e9 wrote: post #64

Earlier quoted context omitted.

I think we might be working something a bit similar and I agree memory is an issue. However it’s not really AGI that will emerge from this. It’s looking very useful but it’s still observable but it’s not a “mind” like an AGI. To add to your comments, I suggest that local vector store of embedding vectors of local content is how I’m going with memory issue. Langchain like. That way all previous progress is tracked and…

> but it’s not a “mind” like an AGI. Please define this. ;)

Please define AGI first ;)

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

#174

Post by rcpt »

MichaelRazum wrote: post #119
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.

"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.

Putnam asked "can a parabola of arc length 4 fit inside the unit circle?"

Should be simple for a computer to just try every parabola but all the LLMs try to solve it like a human would (and get it wrong)

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

#175

Post by ugh123 »

maCDzP wrote: post #4

Am I the only one with an uneasy feeling about all these advancements? Are we going fast or is it just because of the buzz? I have a hard time separating the two. It’s very exiting and I want to keep being exited. I don’t want to become terrified.

'buzz' doesn't usually come with examples!

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

#176

Post by rlt »

michaelmrose wrote: post #159
_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.

An actual intelligence would have a mental model of the world deeper than the connection between one token and the next and a model of the human beings he was interacting with and an expectation of effecting that model to achieve actual differences in the observed world. In other words Google translate doesn't actually speak Chinese.

> An actual intelligence would have a mental model of the world deeper than the connection between one token and the next

Why are you so confident in this? We don't really know how human "intelligence" works. Whose to say it's not doing something similar?

It's a bit like saying an audio file doesn't contain "music" because it's just a binary representation of the original work.

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

#177

Post by Vespasian »

nemo44x wrote: post #108

I always wondered what it was like for people that lived through the discovery of relativity. It must have just been world changing to understand what it meant and how entire perspectives and theories were dead overnight. Just a massive change in the understanding of our existence and the potential it unlocked. These types of things must feel similar.

I don't think relativity had the same hype associated with it.

I'm finding it very difficult to differentiate between (sometimes involuntary) sales people and genuine usefulness (of which there is plenty to be clear).

It is yet unclear where the conceptual and fundamental limitations of the current approach lie and I'm immediately suspicious about anyone telling me there aren't any in particular when this sentiment is based on a few hours of GPT-4 usage.

We need more hard science on this. Great claims require great proofs and "AGI is imminent" is a very very very great claim.

We know that these tool are pretty useful as they are right now and will have massive influence on society.

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

#179

Post by jules »

Workaccount2 wrote: post #128
IanCal wrote: post #88

Earlier quoted context omitted.

> With the unreleased 32,000 token context window, that is really a lot of context when you consider that it can heavily compress things by referencing what it was trained on. Also that means you can just iterate with different contexts until you can deal with the problem. How many problems need 50 pages of context on top of what gpt4 knows for solving the next step?

>How many problems need 50 pages of context on top of what gpt4 knows for solving the next step? Perhaps the unknown unkowns? I envision a scenario where a super intelligent AI seemingly runs off the rails and becomes obsessed with overtly complex problems that are totally intractable to humans. Where we'd be like ants trying to make sense of cell phones.

Maybe it can do this with sleep, where it gets further training on the new input and output it produced that day.

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

#180

Post by jules »

Workaccount2 wrote: post #67
dvt wrote: post #31

Earlier quoted context omitted.

> it turned it from a math dummy to a math genius overnight Imo your post fundamentally misunderstands a few things, but mainly how Wolfram works. Wolfram can be seen as a "database" that stores a lot of human mathematical information (along with related algorithms). Wolfram does not make new math . A corollary here is that AGI needs to have the ability to create new math to be truly AGI. But unless fed something lik…

My definition of "mathematical genius" is simply wider than yours. To me its people who can solve math problems that 99.9% of the population can't without assistance. Which I think is a fair colloquial definition. ChatGPT went from struggling to provide the answer for 20x20 to easily being able to provide the right answer for any math problem wolfram alpha can.

Wolfram Alpha is computation. So it became a computational genius in precisely the things that Wolfram Alpha can do. A better test is whether it can prove new lemmas, like the average undergraduate in mathematics. From what I tried, it cannot do that yet.

I'm convinced that doesn't require a breakthrough in the architecture or scale of LLMs, though. GPT-4 seems plenty smart enough to be able to learn that, if hooked up to a proof assistant like Lean or Coq with the right fine tuning iteration loop.

Post reply on HN