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

71–80 of 280 posts

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

#71

Post by Manjuuu »

karmasimida wrote: post #54
Manjuuu wrote: post #36

Earlier quoted context omitted.

There will be no AGI during our lifetime. It seems weird to me that people that should understand how ML works (e.g. sama) instead of educating laypeople about about how this actually works and the huge limits the technology has, start talking nonsense about AGIs like some random scifi fan at a convention. Depressing.

How can you speak with such confidence, when Hinton and Ilya Sutskever can not? Hinton even said it is possible in next 5-10 years. While, you can believe whatever you believe, please don't bash people as laypeople or something as nonsense.

The same confidence of those already planning for the advent, that will never be, of AGI. I see a lot of unmotivated enthusiasm for the "new" thing, the opinions of Hinton should be considered valid if the reasoning makes sense, not just because the source is Hinton. No idea why he said that it's possible in 10 years.

Not trying to bash anyone, I just meant normal people, outside of the field. Enthusiastic nonsense is still nonsense.

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

#72

Post by dvt »

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.

> To me its people who can solve math problems that 99.9% of the population can't without assistance.

You're just kind of re-emphasizing my point: ChatGPT is using Wolfram as its assistance. So really, it's acting more like a "dumb" API call, not a "math genius" at all.

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

#73

Post by Manjuuu »

fnovd wrote: post #17
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.

We've been "moving too fast" since we figured out agriculture. It's fine. The world as you know it will change irreversibly; you'll long for the simplicity of youth; you will bemoan the state of the world we have left for our children... just like every generation before us did. It'll all be fine. Enjoy the ride, it's called life, and it's better than it ever has been.

We should have had a moratorium on potatoes, look at us now.

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

#74

Post by catchnear4321 »

A lot of LLM/ AI research feels like a big “duh.”

The language model, being trained on essentially the primary way in which humanity communicates, might be a good means of managing integration of less language-focused models.

…duh?

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

#75

Post by _yb2s »

roflyear wrote: post #58
_yb2s wrote: post #28

Earlier quoted context omitted.

GPT-4 can do this. I realize that a description of how these models work implies that this is absolutely impossible , so I have no explanation other than suggesting you go try it out for yourself.

Bro, GPT-4 can absolutely not understand new information. Try to teach it a grammar. It can't learn a grammar. Anyone can learn a new grammar. Not GPT-4. GPT-4 does not ask clarifying questions. It does not understand things.

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 specific values for a, b, and c. Please provide these values so I can calculate the solution(s) for x.

Another example of it thinking about things in a new way:

p: I have on my desk a book, with an apple sitting on top. If I were to suddenly, rapidly remove the book such that the apple remained in place, in which direction would it eventually move?

r: If you suddenly and rapidly remove the book from beneath the apple, the apple would initially stay in place due to its inertia. However, once the book is removed, there would be no support underneath the apple. As a result, the apple would eventually move downwards due to the force of gravity acting on it.

p: Because the earth is a sphere, I prefer to use the terms “in” and “out” to refer to movement relating to that. Can you please rephrase your answer in the terms?

r: Certainly! If you suddenly and rapidly remove the book from beneath the apple, the apple would initially stay in place due to its inertia. However, once the book is removed, there would be no support underneath the apple. As a result, the apple would eventually move "in" towards the center of the Earth, due to the force of gravity acting on it.

(Note I didn't tell it which direction was in vs out. This is the example problem Chomsky gave in his recent article arguing that GPT-3 cannot think - per his ideas no language model would ever be able to answer a question like this. I went a lot deeper with this and got it to add fluid dynamics calculations for wind, etc.)

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

#76

Post by alchemist1e9 »

brotchie wrote: post #29
_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…

Yep, the tipping point for me was seeing a demo of GPT-4 writing code, then being shown exceptions where the code failed, and successfully fixing the code given that feedback. Seems that for any task where you can generate an error signal with some information ("ok, what you just tried to do didn't succeed, here's some information about why it didn't succeed"), GPT-4 can generally handle this information to fix the e…

> Only thing that's really missing is somebody to crack the back of a memory module (perhaps some trick with embeddings and a vector db) is all it takes for this to be AGI.

Here to say I agree with embeddings and vector db for memory systems. However also to disagree this can lead to AGI.

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

#77

Post by chasd00 »

user- wrote: post #5

Its a matter of time until connecting widely different AI tools will be super seamless, very exciting. The examples in the paper are pretty cool. I predict within the next year or so will see an sort of A.I assistant that is hooked up to dozens of LLMs and similar tools, and the end user will just ask their assistant to do things for them. That sci fi moment is almost here.

connecting "widely different AI tools" reminds me of the good old pipe operator. Maybe an AI can be an "anything command" for a specific domain and then we just pipe them together so they can each weigh in with their own expertise. ...like an AI team or committee more or less.

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

#78

Post by catchnear4321 »

quonn wrote: post #7
catchnear4321 wrote: post #6

Earlier quoted context omitted.

Being terrified doesn’t serve much purpose at this point. We are going too fast. Have been for years. This is just the first clear indication. Braking is fatal, but some seem pretty hell-bent. Deceleration is complicated, and it seems highly unlikely that there would be sufficient consensus for true deceleration. Local deceleration is simply waiting for the acceleration occurring somewhere else to overcome your effor…

I disagree. ChatGPT is a clear turning point. We have not been going too fast before, at least not outside LLMs. Singularity is a belief system, it has very little to do with AI. edit: I also think if we would ever get to a point where AI gets close to a point of possibly getting out of control as you imply it would simply be banned in the US/Canada/EU/Australia. Furthermore Latin America and Africa could and would b…

I wasn’t limiting my comment to AI development.

Humanity has been going too fast for a long time.

Tell me about this singularity belief system. I simply meant something stronger than an inflection point, closer to the mathematical sense than what you must be assuming, but that word must mean something more for you.

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

#79

Post by nomel »

marcosdumay wrote: post #42
_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 believe you will quickly run into a barrier due to the small size of the context window. And increasing the context window gets harder and harder the larger it is. There's a sibling talking about internal memory. That's how our brains solve the issue. AFAIK, nobody knows how to train something like it.

I think an attention/focus system might be applicable. I think humans have the same limitations, with tricks to work around it. As Jim Keller once said on an Lex Fridman interview, a good engineer is one that can jump around between the different levels of abstraction. We think in a high level, then "focus" and jump down when needed.

I think something like this could be hacked together, with summarization and parallel "focus threads", containing prompts that focus on details. These could be pruned/merged back together, to add to the "summary" higher level abstractions.

I use this approach already, to some extent, when a conversation gets too long and I need specific details. I'll start a new prompt, include a high level summary, and then "focus" on specific ideas to get more specific answers about a particular detail.

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

#80

Post by catchnear4321 »

quonn wrote: post #39
catchnear4321 wrote: post #6

Earlier quoted context omitted.

Being terrified doesn’t serve much purpose at this point. We are going too fast. Have been for years. This is just the first clear indication. Braking is fatal, but some seem pretty hell-bent. Deceleration is complicated, and it seems highly unlikely that there would be sufficient consensus for true deceleration. Local deceleration is simply waiting for the acceleration occurring somewhere else to overcome your effor…

Have to reply a second time: It does serve a purpose. There is a purpose in fear and the purpose is to either get us moving if we are complacent or to prevent us from doing things that are not good for us. So the fear may be justified. Maybe.

Time to do something more than respond to cortisol. Before something smarter than the monkey decides to guide the monkey effectively.
Post reply on HN