HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace • Hacker News Board

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

#211

Post by qolop » Sat, Apr 01, 2023, 11:32 AM UTC

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…

>> It's still just predicting the next word

Predicting the next word is a much deeper problem than people like you realise. To be able to be good at predicting the next word you need to have an internal model of the reality that produced that next word.

GPT-4 might be trained at predicting the next word, but in that process it learns a very deep representation of our world. That explains how it has an intuition for colours despite never having seen colours. It explains why it knows how physical objects in the real world interact.

Now, if you disagree with this hypothesis it's very easy to disprove it by presenting a problem to GPT4 that is very easy for humans to solve but not for GPT4. Like the Yann Lecun gear problem, which GPT4 is also able to solve.

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

#212

Post by ilaksh » Sat, Apr 01, 2023, 11:49 AM UTC

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 think that's a misinterpretation of what these types of papers are.

GPT3.5 and GPT4 are already general purpose with text tasks. You can give it _any_ well defined programming task that involves a fairly direct route from natural language to code, along with the API/module description (or output data format), and it can do it. That's the only reason this and 500 other papers or services like it (but doing different things) are possible.

3.5 is not multimodal though. That's why it needs the other models. But GPT4 has image understanding and can do a lot of these things without the external tools.

There is no reason to think that similar variations of GPT will not be able to handle video understanding or generation at some point.

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

#213

Post by _yb2s » Sat, Apr 01, 2023, 12:26 PM UTC

roflyear wrote: post #139

_yb2s wrote: post #75

Earlier quoted context omitted.

I'm not sure why you think that? When I give it programming tasks, GPT-4 will ask all kinds of clarifying questions. Here is a trivial example: p: I want you to solve for x, giving me a numeric value, given the formula ax^2 + bx + c = 0. r: To find the numeric value of x for the quadratic equation ax^2 + bx + c = 0, we need to use the quadratic formula: x = (-b ± √(b^2 - 4ac)) / (2a) However, you haven't provided spe…

First, these are trivial examples. I would not classify "give me the values to this math formula" as clarifying questions. Second, in response to "I'm not sure why you think that?" ask GPT why it often does not ask clarifying questions. It will explain to you why! Third, I just asked GPT the most vague question on the planet: "I am trying to create a function that takes a value, and gives me a result using that value…

I appreciate your willingness to engage with real examples on this so we’re not just talking past each other.

I on purpose chose the most simple concise examples that demonstrate the classes of thought capabilities you were saying it was missing, it can also do more challenging versions of these type of problems.

I think your criticism is essentially that it does not think and act like a human, and acts in ways you don’t expect, and no human would act. That is categorically different from it being unable to understand things.

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

#214

Post by _yb2s » Sat, Apr 01, 2023, 12:39 PM UTC

aezart wrote: post #192

rlt wrote: post #176

Earlier quoted context omitted.

> 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.

If I ask a human what their favorite flavor of ice cream is, they will answer based on their actual preference for different kinds of ice cream. If I ask a chat LLM what its favorite flavor of ice cream is, it will select a statistically likely answer to the question. That's the difference. For reference: my favorite ice cream flavor is cake batter, but only if it's the one at Cold Stone. If it's from somewhere else,…

It seems to me that most of these arguments boil down to “it didn’t think or respond like I would expect a human to, therefore it isn’t intelligent.” This isn’t open minded to the diverse possibilities of non human intelligence, nor is it demonstrating a lack of understanding or real limitation. It doesn’t seem to have any sense of self beyond playing characters it was asked to play, yet those characters are able to intelligently select actions towards goals they were assigned by a prompt using creativity, complex reasoning, and deep understanding. This is a difference that isn’t an inferiority or shortcoming.

I would even argue that humans are more similar to that than we think. The main difference is that one of the characters is locked to the surface most of the time (not even very perfectly).

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

#215

Post by _yb2s » Sat, Apr 01, 2023, 1:00 PM UTC

knome wrote: post #89

_yb2s wrote: post #19

Earlier quoted context omitted.

I agree, I suspect AGI is possible right now with a similar system only slightly more sophisticated than this one. The right "glue" for existing models, and plugins to existing data sources all coordinated in a system. GTP-4 would do the managing, and handling, and some simple template API and handler script would allow it to call instances of itself or other models, track recursion depth, and automatically remind GT…

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 like the boats can’t swim summary of this disagreement. I think these two groups have been talking past each other, and this is the crux of the disagreement. Some people seem to expect AI to converge to being more like a human as it gets better and are stuck on how inhuman it is. They are not considering the endless possible types of non human intelligence. These differences should not be mistaken as inferiority, in many cases they will offer huge advantages.

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

#216

Post by sebzim4500 » Sat, Apr 01, 2023, 1:27 PM UTC

fnimick wrote: post #104

Mizza wrote: post #70

Earlier quoted context omitted.

I've built a service for building systems like this. I haven't officially "launched" yet, but it's working and you can play with it here, if anybody is up to giving the alpha a spin: https://aistudio.fly.dev/

It's oddly fitting that your example workflow appears to be scraping content from elsewhere, rewording it, and generating an image in order to produce automated blogspam.

He knows his audience maybe too well.

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

#217

Post by melagonster » Sat, Apr 01, 2023, 1:28 PM UTC

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.

you belittle a person by call him worse than AI, again and again. it almost like you just want to belittle human being.

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

#218

Post by _yb2s » Sat, Apr 01, 2023, 1:39 PM UTC

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 specific example proves conceptual understanding of the subject matter.

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

#219

Post by namelos » Sat, Apr 01, 2023, 1:44 PM UTC

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…

> It's still just predicting the next word.

Computer-generated random numbers are not truly random, yet they are practically random in most real-world use cases. You can’t easily cheat the RNG in World of Warcraft to get critical strike every time.

The output from GPT is generally very intelligent and versatile in terms of text. It may even be capable of handling more multi-modal problems with the use of enough sensors and motors. Perhaps the same idea of "predicting the next move" or "predicting the next idea" can still apply.

Who knows, maybe humans are essentially physical creatures that "generate the next thought and generate the next move"?

One of the biggest issues with GPT is its lack of mid-term memory like human do. Instead, we need vector store and search then bolt back its short term memory instead of letting it handle everything in a more coherent way. Perhaps it could benefit from lightweight fine-tuning technologies like LoRA and hypernetworks for stable diffusion. If this issue is resolved we would see it'll get even more practical. Again, the flaw is not about "predicting the next words".

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

#220

Post by roflyear » Sat, Apr 01, 2023, 1:57 PM UTC

bjackman wrote: post #187

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 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…

It's not a big just. Saying it is AGI is an insanely huge claim. Don't flip it around and saying the skeptic is the one making a large claim. They aren't!