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

#191

Post by deepnet » Sat, Apr 01, 2023, 8:38 AM UTC

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…

Add a expert human in the loop, e.g. Terence Tao and this might be feasible.

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

#192

Post by aezart » Sat, Apr 01, 2023, 8:44 AM UTC

rlt wrote: post #176

michaelmrose wrote: post #159

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 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.

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, I go with cookie dough.

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

#193

Post by SanderNL » Sat, Apr 01, 2023, 8:54 AM UTC

roflyear wrote: post #62

marshray wrote: post #49

Earlier quoted context omitted.

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.

It is writing a book. You need to set the stage properly so “asking questions” will become part of its story. Roleplay. It is not a being, there is no feedback loop, no motivation. If it is said to want something I think you can say it wants to finish the text. Whatever it is.

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

#194

Post by stavros » Sat, Apr 01, 2023, 8:59 AM 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…

Stavros' law of AGI: If we know how it works, it's not true AGI.

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

#195

Post by r_singh » Sat, Apr 01, 2023, 9:10 AM 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…

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.

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

#196

Post by mmiliauskas » Sat, Apr 01, 2023, 9:12 AM 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…

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.

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

#197

Post by espadrine » Sat, Apr 01, 2023, 9:13 AM 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'd like the "stochastic parrot" crew to explain how interactions like this somehow don't involve the extraction of and manipulation of abstract meaning.

They don’t claim that it doesn’t. What they point out is that humans have a tendency to ascribe intent and agency to the text it outputs. But the LLM is optimized for prediction, not survival, unlike humans[0]:

> Text generated by an LM is not grounded in communicative intent. […] Our perception of natural language [is mediated by] our predisposition to interpret communicative acts as conveying coherent meaning and intent

Some of the dangers they raise associated with this is that it will not realize that words it chooses are PII, dangerous to give to who they are talking to, or biased in a way that can cause societal harm:

> If the LM or word embeddings derived from it are used as components in a text classification system, these biases can lead to allocational and/or reputational harms. […] A Palestinian man [was] arrested by Israeli police, after MT translated his Facebook post which said “good morning” (in Arabic) to “hurt them” (in English).

What they encourage is to view it as a tool and assess how it may fail. For instance, you might object that the MT was simply incorrect; but realistically, sentences can be translated in many ways and with many intents (eg. Allah Akbar has a lot of contexts!) and the LLM may not be given the full picture of the situation.

The stochastic parrots paper is heavily misrepresented or used by people that don’t seem like they read it. For instance, it was cited in a recent petition asking to stop work on powerful AI, prompting a response from the authors[1] pointing out that it misunderstands the paper and emphasizing that they disagree with the petition.

[0]: https://dl.acm.org/doi/pdf/10.1145/3442188.3445922

[1]: https://www.dair-institute.org/blog/letter-statement-March20...

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

#198

Post by anonkogudhyfhhf » Sat, Apr 01, 2023, 9:18 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…

Evolution is just gene selection through natural selection. To create an eye is not possible

Well neural networks have unpredicted emergent properties. I don't see how anyone can rule out or know future behaviour

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

#199

Post by sillysaurusx » Sat, Apr 01, 2023, 9:23 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…

> less data, more sophisticated architectures

“The bitter lesson” would like to have a word. http://www.incompleteideas.net/IncIdeas/BitterLesson.html

I appreciate your enthusiasm, but the history of ML shows that your approach is less likely to work. Maybe you’ll be the one to prove everyone else wrong. Architectural breakthroughs are few and far between, and it’s incredibly difficult to reason about. I came up with the Lion optimizer while Google was using random tree search across 300 TPUs to discover the same thing, and it’s just five lines or so.

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

#200

Post by bjackman » Sat, Apr 01, 2023, 9:30 AM UTC

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.

Guess what, I just saw one of those idiots from the bronzeworking tribe with a BENT sword. Imagine using weapons with blades that can get bent.