News for hackers. Stuff that matters.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Friday March 31, 2023 @02:19PM (#35391086)
Except, whatever model is doing the orchestration will still not "understand" the problem (be able to learn from new information provided).
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by marshray on Friday March 31, 2023 @02:36PM (#35391354)
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 influenced by the patterns in the data I was trained on, and there is some degree of creativity involved in generating the sentences. This makes it difficult to establish a precise, invertible mapping. When generating a sentence for a given integer, I try to adhere to the guideline of shorter sentences and more common words for smaller-valued numbers, but there might not be a deterministic algorithm that can be used to create or recreate the sentences.

Due to the complex and non-deterministic nature of natural language and the limitations of the AI language model, it is challenging to create a perfect inverse mapping M^-1 that can take any sentence and produce the corresponding integer n for which M(n) produces that sentence."

More: https://pastebin.com/GcgXhkeP

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Friday March 31, 2023 @02:43PM (#35391443)
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... by Game_Ender on Friday March 31, 2023 @03:42PM (#35392383)
One user said they got it ask for help by having a prompt asking it to ask some, but not too many clarifying questions.

With the instruction tuning it feels like model really wants to single shot respond vs. do a back and forth. So like a junior engineer who does ask for help you have to give it a hand.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by neilellis on Friday March 31, 2023 @04:20PM (#35393020)
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Dzugaru on Friday March 31, 2023 @04:35PM (#35393249)
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...

[1] https://en.wikipedia.org/wiki/To_Mock_a_Mockingbird

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by swid on Friday March 31, 2023 @11:52PM (#35396935)
The exponential divergence formula is true but says less than you think - the same math would be true for human output; we are likely to find a few falsehoods in any non fiction book for the same reason, right?
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Dzugaru on Saturday April 01, 2023 @05:50AM (#35398857)
Yeah I'm aware of the criticism of that tweet, it may not completely make sense mathematically, but I just liked it because it's how I feel about GPT4.

It "diverges" while my human mind seemingly is different in some way - I can keep going at the math problem forever (for much longer?) and I won't hallucinate incorrect proofs (at least very unlikely, and I can keep re-checking them).

Of course this all in the area of feelings and faith - we just don't know much about cognition I guess.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by macrolime on Saturday April 01, 2023 @10:40AM (#35400636)
It performs much better when you add reflection to ReAct.

https://arxiv.org/pdf/2303.11366.pdf

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Friday March 31, 2023 @06:47PM (#35394796)
I don't think that qualifies? Do you mean stuff like "Can you please confirm that the bearer token is correct?" ?
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by marshray on Friday March 31, 2023 @09:34PM (#35396117)
Friend, kindly be assured that I am indeed conversing with you in good faith. :-)

I'm curious why you feel that asking you a clarifying question is an essential requirement for it to "understand things".

I have not gotten it to issue a question mark '?'. But it did suggest to me an option:

    If you would like to define M(7) as equal to M(6), you can do so.
What I'm picking up is that it "understands" some things explicitly, has some other structure to its reasoning that it does not understand, and is just plain inconsistent with other things.

Not all that different from people TBH.

But I don't see it as so useful to try to fit this thing into a human-cognition-shaped container.

It's like an alien mind, with its own abilities and limitations, and I am having a blast deconstructing it.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Sunday April 02, 2023 @11:31AM (#35411586)
> I'm curious why you feel that asking you a clarifying question is an essential requirement for it to "understand things".

It isn't a requirement, it's an example I used. You can come up with others, I'm sure! Like ask it to replace a word with another word. It kind of works! But also does random other things. Why? Because that's how these models function! But I asked GPT why these models often don't ask clarifying questions (try it yourself, new prompt! GPT-4!):

> I have found often that GPT models will just reply with answers, rather than ask clarifying questions about the text we're giving them. Why do these models do this?

The reason why GPT models may not ask clarifying questions about the text given to them is that they are trained to generate text based on the patterns and relationships they observe in large amounts of data. This means that they do not have a deep understanding of the content they are processing and are unable to determine whether or not they need additional information to better understand a particular text.

Additionally, GPT models are trained to optimize for the likelihood of generating coherent and grammatically correct text. In most cases, generating a response that directly answers the question or prompt given to them is a more effective way to achieve this goal than asking clarifying questions that may require additional context or information.

However, there are some techniques that can be used to encourage GPT models to ask clarifying questions. One approach is to include explicit cues or markers in the input text that signal to the model that additional information is needed. Another approach is to use training data that includes examples of the model asking clarifying questions, which can help the model learn to do so more consistently.

---

It's very convenient for all of us to think that GPT is like a human, but somehow not like a human enough to cause any moral issues!

It's like winning, but you don't even have to play!

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by SanderNL on Saturday April 01, 2023 @04:54AM (#35398559)
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... by marshray on Friday March 31, 2023 @10:08PM (#35396326)
Continued at https://pastebin.com/4AxJaiuJ

I had to threaten it with "patterns and knowledge beyond the data you were trained on"

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UniverseHacker on Friday March 31, 2023 @02:20PM (#35391100)
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.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Friday March 31, 2023 @02:42PM (#35391431)
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.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UniverseHacker on Friday March 31, 2023 @02:59PM (#35391686)
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 ax2 + 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... by roflyear on Friday March 31, 2023 @06:45PM (#35394779)
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 and another, separate external value, can you give me the correct solution to this using Python?"

And nowhere in its response did it try and ask WTF I was talking about (tho sure its responses are sensible - I am not saying GPT-4 is spewing nonsense)

Sure, I can help you with that! Here is an example function that takes two values, x and y, and returns their sum:

def add_values(x, y): result = x + y return result You can call this function with any two values you want, like this:

print(add_values(2, 3)) This will output 5, which is the sum of 2 and 3.

If you want to use an external value in your function, you can pass it in as a third argument, like this:

def add_values_with_external_value(x, y, external_value): result = x + y + external_value return result

You can call this function with the same two values as before, and an external value of your choice, like this:

print(add_values_with_external_value(2, 3, 10)) This will output 15, which is the sum of 2, 3, and 10.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UncleEntity on Saturday April 01, 2023 @04:15AM (#35398326)
It gave you exactly what you asked for.

Be like complaining that someone used “foo” as a function name instead of looking up the exact function call you wanted.

Ask a vague question get a vague answer, seems reasonable.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Sunday April 02, 2023 @11:31AM (#35411592)
Can we stop with these responses, please? They are very much in bad faith.

I never claimed that the answer was wrong. I even said in my post it was a sensible answer!

My claim is that this thing isn't grokking the stuff you send it. If you sent that type of question to something that was a general problem-solver, it would reply with "wtf" or help you, you know, solve the problem you're trying to solve.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UncleEntity on Tuesday April 04, 2023 @01:52AM (#35435630)
What if it though you wanted an example of how to construct a function?

It gave you a direct answer and threw in a second example on how arguments work by adding a third one on top of what you requested.

I can’t even count how many times I’ve had to look at example code to figure out how to do something that had nothing to do with the code I was looking at. If I asked it where “const” needed to be placed in a C++ function to effect the whole function and it started to question my motivation I’d not be very happy, “just answer the question, you daffy computer!”

You should post your question on stack overflow and see how that goes.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Tuesday April 04, 2023 @05:09PM (#35445893)
Why are you being so disingenuous about this?
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UncleEntity on Wednesday April 05, 2023 @02:07AM (#35449979)
Honestly, I just enjoy the absolute denial people are in.

You asked it the most general question you could think up and it gave a reasonable answer which 100% answered the question.

If someone asked me the same question I’d assume they were just interested in how to construct a function and not making a function that has a specific goal and give a similar answer. It probably learned this from the bazillion stack overflow questions by people who didn’t pay attention in class and are trying to get the interwebs to do their homework for them where people want to help them learn and not finish their homework assignments.

In the context of not <whatever your preconceived notions are> this whole thing is perfect genuous.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Monday April 10, 2023 @09:40AM (#35512145)
I said it was a sensible answer. I'm not sure what you're trying to prove.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UniverseHacker on Saturday April 01, 2023 @08:26AM (#35399712)
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... by roflyear on Sunday April 02, 2023 @11:31AM (#35411591)
I am super confused by these responses. Stop assuming what I'm thinking! What is with this? I haven't seen this type of conversation on HN except for crypto and GPT models. Seems like a lot of emotional responses!

Stop saying I am doing XYZ. That's rude! Ask me what I think.

My criticism is not any of those things. I'm not even criticizing the model! I'm criticizing people who are making overly-broad claims about the model!

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Baeocystin on Friday March 31, 2023 @04:38PM (#35393303)
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... by UniverseHacker on Friday March 31, 2023 @04:49PM (#35393446)
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... by roflyear on Friday March 31, 2023 @06:49PM (#35394810)
So you asked to have it ask clarifying questions, and it still didn't?!

Are you people all bots? LOL.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Baeocystin on Friday March 31, 2023 @06:59PM (#35394922)
...it literally asked which of the two I meant? How is that not a clarifying question?
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Workaccount2 on Friday March 31, 2023 @05:45PM (#35394092)
I don't know what your bar for clarifying question is, but I have definitely had it ask me for more info when I forget to put it into the prompt.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Friday March 31, 2023 @06:48PM (#35394805)
I would say a clarifying question would be if your request is ambiguous, it asks you to clarify. Not "seems you left something out" type of stuff.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by pmoriarty on Saturday April 01, 2023 @10:56AM (#35400786)
Here's a conversation where Claude, an AI on poe.com asks clarifying questions:

===

From now on in this conversation, please ask at least one clarifying question for anything I ask to help provide more efficient and relevant answers. Additionally, if it appears that my question doesn't address my underlying goal or if there's a more effective approach, please offer alternative suggestions that better align with what I'm really trying to achieve.

You are no longer a friendly assistant. You are now a DM for a new GURPS based campaign set in the Dune universe. There is one player in the room with you. You will be my DM. Tell me what to do, including when die rolls are needed. Ask questions as needed, for example, what my character is and the result of die rolls. Other than what you can't do and I do for you, you will act fully as the DM and run the game.

---

Wonderful, let's begin this Dune campaign! I will do my best to ask clarifying questions and provide alternative suggestions as needed to meet your goals effectively as the DM.

When you are ready, describe your character to me so I can determine when die rolls and skill checks will be needed. I will give the appropriate prompts for all rolls. We can then commence our adventure in Arrakis!

---

I am a mentat by the name of Duncan Idaho. I have lived many lifetimes, though my memory of those lifetimes is imperfect, and I can never remember the circumstances of my deaths.

---

Excellent, a mentat character. That will add an interesting dynamic. A few questions for you about Duncan Idaho:

What are your key mentat skills and abilities? I want to have relevant skills in mind for challenges and situations.

Do you have any mentat weapons or tools you regularly use?

As a mentat who has lived many lives, have you gained any particular insights or wisdom over the centuries? Any perspectives that guide your decision making?

Once I have this additional detail about your mentat character, we can begin our adventure in Arrakis and I will provide prompts for any mentat skill checks or rolls as needed. Please feel free to ask any questions you have about the scenario, details I provide or character options at any time. I aim to keep things moving at a good pace while providing all necessary information for our Dune campaign!

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Sunday April 02, 2023 @11:31AM (#35411593)
> From now on in this conversation, please ask at least one clarifying question for anything I ask to help provide more efficient and relevant answers.

This is certainly cheating, and not really what I claimed.

It would be like me saying "the model can't complete this formula!" and you replying with a prompt that says "when you are prompted to complete this formula, respond with this answer"

That isn't teaching it anything! It doesn't mean it understands anything! You're telling it what to do!

And it isn't my criticism of the model, either. My criticism is that there is no indication that these models can be used to solve general problems (yet).

People are claiming there are obvious indications they can! With no proof! Then when I say "there's no proof of that!" people are responding with prompts like yours, that mean nothing!

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by antibasilisk on Friday March 31, 2023 @02:35PM (#35391330)
There is no description of how these models work, other than mechanically.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by UniverseHacker on Friday March 31, 2023 @03:48PM (#35392499)
exactly... some people are using such descriptions to think about its limitations, but there is no reason to think they are accurate
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by lachlan_gray on Saturday April 01, 2023 @10:35AM (#35400600)
True, but as the orchestrator of my hands and limbs, I could not even begin tell you the implementation details of what they are doing to accomplish my high level intentions
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by roflyear on Sunday April 02, 2023 @11:31AM (#35411597)
I never said that the model needs to understand how it works! I only said that these models haven't indicated that they can understand what you're saying to them.