Can we please stop generating bounding boxes and instead generate a proper segmentation using bitmasks?
it depends on the problem?
HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
111–120 of 280 posts
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#112Earlier quoted context omitted.
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.
ReAct will, example: https://github.com/neilellis/coding-with-gpt-4/blob/main/lan...
It definitely can "understand" things is some way, however I'm pretty sure ReAct or similar will give it just a nudge forward and the underlying problem of it hallucinating and not being "lucid enough" is not so easily solved.
In the original ReAct paper it falls apart almost immediately in ALFWorld (this is a classical test for AI systems - to be able to reason logically - and it still isn't generally solvable due to combinatorial explosion).
For now it requires human correction looped or not, or else it "diverges" (I like Yann Lecun explanation [0]).
In my own experiments (I haven't played with LangChain or ReAct yet) it diverges irrecoverably pretty quickly. I was trying to explain to it the elementary combinators theory, in the style of Raymond Smullyan and his birds [1] and it can't even prove the first theorem (despite being familiar with the book). A human can prove it knowing almost nothing about math whatsoever, maybe it will take a couple of days thinking, but the correct proof is not that hard - just two steps.
[0] https://www.linkedin.com/posts/yann-lecun_i-have-claimed-tha...
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#113Earlier quoted context omitted.
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...
Thanks for book refs. Would you recommend any of them for a bright teen? [1] sounded like a good candidate.
Yep, they're both super approachable, [1] is a great way to get introduced to some deep philosophy in a fun way.
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#114Earlier 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 just tried this small example right now as a test: https://i.imgur.com/p4s7HCU.png
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#115Earlier quoted context omitted.
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.
He's not really saying that GPT-4 is a 'math genius', rather the combined system of GPT-4 and Wolfram is.
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#116Earlier quoted context omitted.
Sorry but nope. GPT-4 is plenty intelligent. I've begun to question the intelligence of anyone that reduces it to "stochastic parrot" because they're not even arguing against results but arbitrary lines drawn on sand. The "We'll see it when it comes" line is just utterly wrong, If there's one thing experts seem to agree on is that not everyone will agree when current definition of agi does arrive. The philosophical z…
> The philosophical zombie is an excellent example of the extent of post shifting we're capable of. I was with you until here. That has nothing to do with this. That argument is about separating intelligence from having a subjective experience, not moving goalposts for intelligence.
It's a tangential relation but it's a relation. I don't think i would say it has nothing to do with it. Goal posts shifting in the field of machine learning isn't just about the posts for defining intelligence. It's broader and deeper than that.
I brought it up because i thought it fit the point i was driving at. Humans/people don't see subjective experience. I don't know that you're actually having some subjective experience. I'm working on what i see and results, same as you.
If you have two unknown equations but one condition - these 2 equations return the same output with the same input. well, then any mathematician would tell you the obvious - the 2 equations are equal or equivalent. it doesn't actually matter what they look like.
This is just an illustration. The point i'm driving at here is that true distinction shows in results. It's a concept that's pretty easy to understand. Yet turn to artificial intelligence and it just seems to break down. People making weird assertions all over the place not because they have been warranted in any empirical, qualitative or quantitative manner but because there seems to be this inability to engage with results...like we do with each other.
when i show the output that clearly demonstrates reasoning and understand, the arguments quickly shift to "it's not real understanding!" and it's honestly very bizarre. What kind of meaningful distinction can't show itself, can't be tested for ? If it does exist then it's not meaningful.
I think that the same reason people shift posts for intelligence is the same reason people fear the philosophical zombie.
idk maybe i'm rambling at this point but just my thoughts.
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#117Earlier quoted context omitted.
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 just tried this small example right now as a test: https://i.imgur.com/p4s7HCU.png
This is a good point, that also works well when managing people. Telling it that it is expected to ask questions really helps, but in my experience it usually will do so anyway, or at least mention what information it is missing and try to reason as well as it can without it.
If it couldn't do this, the whole concept here would be moot... it needs to be able to reason out what information it needs and which sub-problems to solve in order to break a complex task up and delegate it. And it is very good at this!
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#118Earlier quoted context omitted.
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.
These rah rah comments aren't illuminating or helpful. There are immense costs - societal and ecological - to progress that a lot of people seem to be blind to, whether willfully or not.
One can reasonably argue that the printing press was responsible for the speed and violence of the reformation. But the alternative of an illiterate world is hardly a panacea. Most large-scale advancements have the same flavor.
What are we to do, then? No snark, honest question.
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#119I 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.
Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace
#120Earlier quoted context omitted.
The power to seriously harm nations may be in the hands of tens of thousands of individuals within a few years. Things might just be different this time.
It will be different this time, just like it was every other time. It still doesn't matter. The epoch of earth's history that happens to overlap with your own lifespan isn't inherently more interesting or important than any other time, except to you. But sure, what good is an exciting new frontier without a gaggle of doomers worried about what's on the other side? Same as it ever was.
>The epoch of earth's history that happens to overlap with your own lifespan isn't inherently more interesting or important than any other time, except to you
Earth's history, sure. Humanity's history though? Living during the Apollo program is clearly more interesting than living in a period of relative stasis. Living during the AGI revolution could be more interesting still, we'll have to see.