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

61–70 of 280 posts

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

#61

Post by nomel »

_yb2s wrote: post #19
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 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 suspect AGI is possible right now with the right "glue" for existing models, and plugins to existing data sources all coordinated in a system.

I think the regulation of the feedback loops required for sustained, deliberate thought, and interaction with the world, will be the most difficult piece of the AGI puzzle, and might not exist today.

New ideas are "hallucinations" of our "existing data", that we eventually get around to proving. An AGI will require these "hallucinations", inhibition and excitation of them. I think it's going to be a tricky balance [1], for sane output.

1. "Creative minds 'mimic schizophrenia", https://www.bbc.com/news/10154775

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

#62

Post by roflyear »

marshray wrote: post #49
roflyear wrote: post #26

Earlier quoted context omitted.

Except, whatever model is doing the orchestration will still not "understand" the problem (be able to learn from new information provided).

Have you actually tried it? GPT-4: "The forward mapping M that I created to map positive integers to English sentences is based on a general guideline, where smaller-valued numbers generally correspond to shorter sentences using more common words. However, this mapping is not a perfect bijection, meaning there isn't necessarily a one-to-one correspondence between integers and sentences. The generation of sentences is…

I am getting super tired of these responses.

Yes, I have tried it. Please converse in good faith.

GPT-4 has never, not once, in dozens of hours of use, asked me a clarifying question.

It cannot understand things.

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

#64

Post by alchemist1e9 »

_yb2s wrote: post #23
basch wrote: post #20

Earlier quoted context omitted.

It also, in my pay opinion, needs a memory store. I need to be able to save something to a variable and call back that exact variable. Right now, because it’s just pure text input of the whole conversation, it can forget or corrupt it’s “memory”. Even something like writing a movie script doesn’t work if it constantly forgets characters names or settings or plot points.

My description above includes a memory store. It is a single variable that it can save and recover, and will automatically get sent back to it at regular intervals if it forgets it saved anything. Only a single text string variable is needed, as GTP-4 is smart enough to realize it can compress, pickle, etc. as many things as it needs into that.

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 retrievable. That way the system can retrieve all it’s “memories” itself. The recursive multi agent pattern is big deal in my opinion.

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

#65

Post by _yb2s »

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.

You are right, but it is unclear to me where this limitation will fall in terms of actual abilities.

GPT-4 can divide large tasks up into logical steps and instructions that can be worked on independently by other instances, and it can create "compressed" condensed explanations of it's own state that can be stored externally and repeated back to it, or passed back and forth between instances. 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.

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

#66

Post by eternalban »

dvt wrote: post #47
Sivart13 wrote: post #40

Earlier quoted context omitted.

If the litmus test for intelligence is the ability to “create new math” most people on earth wouldn’t be considered intelligent

> If the litmus test for intelligence Moving goal posts around is unhelpful. I think my comment was pretty clear in the context of AGI and calling ChatGPT a "math genius."

Will you settle for whiz?

Interesting q for us to consider is how do we come up with "new ideas". I think we can consider play (in the abstract sense) to be a significant element of the process. Play is a pleasurable self-motivated activity.

I am certain an AGI (if such a thing exists) will need to be playful.

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

#67

Post by Workaccount2 »

dvt wrote: post #31
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.

> 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.

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

#68

Post by chasd00 »

Sivart13 wrote: post #40
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…

If the litmus test for intelligence is the ability to “create new math” most people on earth wouldn’t be considered intelligent

that reminds me of this scene in irobot

spooner> You are a clever imitation of life... Can a robot write a symphony? Can a robot take a blank canvas and turn it into a masterpiece?

sonny> Can you?

edit: i just realized OpenAI can answer both of those questions with "yes." ...

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

#69

Post by dvt »

eternalban wrote: post #66
dvt wrote: post #47

Earlier quoted context omitted.

> If the litmus test for intelligence Moving goal posts around is unhelpful. I think my comment was pretty clear in the context of AGI and calling ChatGPT a "math genius."

Will you settle for whiz? Interesting q for us to consider is how do we come up with "new ideas". I think we can consider play (in the abstract sense) to be a significant element of the process. Play is a pleasurable self-motivated activity . I am certain an AGI (if such a thing exists) will need to be playful.

Totally agree. Recently read Finite and Infinite Games[1] and The Grasshopper: Life, Games, and Utopia[2] and I'm more or less convinced motivations are always essentially games.

[1] https://www.amazon.com/Finite-Infinite-Games-James-Carse/dp/...

[2] https://www.amazon.com/Grasshopper-Third-Games-Life-Utopia/d...

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

#70

Post by Mizza »

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'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/

Post reply on HN