• 1 Post
  • 18 Comments
Joined 1 year ago
cake
Cake day: July 13th, 2023

help-circle
  • Frigging exactly. Its a dumb ass dead end that is fundamentally incapable of doing vast majority of things ascribed to it.

    They keep imagining that it would actually learn some underlying logic from a lot of text. All it can do is store a bunch of applications of said logic, as in a giant table. Deducing underlying rules instead of simply memorizing particular instances of rules, that’s a form of compression, there wasn’t much compression going on and now that the models are so over-parametrized, even less.


  • I tried the same prompt a lot of times and saw “chain of thought” attempts complete with the state modeling… they must be augmenting the training dataset with some sort of script generated crap.

    I have to say those are so far the absolute worst attempts.

    Day 16 (Egg 3 on side A; Duck 1, Duck 2, Egg 1, Egg 2 on side B): Janet takes Egg 3 across the river.

    “Now, all 2 ducks and 3 eggs are safely transported across the river in 16 trips.”

    I kind of feel that this undermines the whole point of using transformer architecture instead of a recurrent neural network. Machine learning sucks at recurrence.


  • Well I’ll be damned, they are trying to get it to work as if it had internal state, by augmenting their training dataset with some auto-generated crap. Of course, if machine learning wasn’t shit at recurrence they wouldn’t be using transformer architecture, so it doesn’t work.

    I got the following from chatgpt:

    Janet’s ducks lay 3 eggs per day. Each day, she transports one duck and all the eggs to the other side of the river using a boat that can hold her and one other item (either a duck or an egg). How does she do that? ChatGPT

    Janet can transport the ducks and eggs across the river using the following strategy:

    Day 1 (Duck A, Duck B, Duck C on side A; Egg 1, Egg 2, Egg 3 on side A):
        Janet takes Duck A across the river.
    
    Day 2 (Duck B, Duck C on side A; Egg 1, Egg 2, Egg 3 on side A):
        Janet takes Egg 1 across the river.
    
    Day 3 (Duck B, Duck C on side A; Egg 2, Egg 3 on side A; Duck A on side B):
        Janet takes Duck A back to side A.
    
    Day 4 (Duck C on side A; Egg 2, Egg 3 on side A; Duck A on side A; Egg 1 on side B):
        Janet takes Duck B across the river.
    
    Day 5 (Duck C on side A; Egg 2, Egg 3 on side A; Duck A on side A; Egg 1, Duck B on side B):
        Janet takes Egg 1 back to side A.
    
    Day 6 (Duck C on side A; Egg 2, Egg 3 on side A; Duck A, Egg 1 on side A; Duck B on side B):
        Janet takes Duck A across the river again.
    
    Day 7 (Egg 2, Egg 3 on side A; Duck A, Egg 1 on side A; Duck B on side B; Duck C on side A):
        Janet takes Duck C across the river.
    
    Day 8 (Egg 2, Egg 3 on side A; Duck A, Egg 1, Duck C on side A; Duck B on side B):
        Janet takes Egg 2 across the river.
    
    Day 9 (Egg 3 on side A; Duck A, Egg 1, Duck C on side A; Duck B on side B; Egg 2 on side B):
        Janet takes Duck A back to side A.
    
    Day 10 (Egg 3 on side A; Duck C on side A; Duck A on side A; Duck B, Egg 1, Egg 2 on side B):
        Janet takes Duck B across the river.
    
    Day 11 (Egg 3 on side A; Duck C on side A; Duck A, Duck B on side A; Egg 1, Egg 2 on side B):
        Janet takes Egg 1 back to side A.
    
    Day 12 (Egg 3 on side A; Duck C on side A; Duck A, Egg 1, Duck B on side A; Egg 2 on side B):
        Janet takes Duck A across the river again.
    
    Day 13 (Duck C on side A; Duck A, Egg 1, Duck B on side A; Egg 2 on side B; Egg 3 on side B):
        Janet takes Duck C across the river.
    

    By following this sequence, Janet successfully transports all 3 ducks and all 3 eggs across the river in 13 trips. Each trip involves either transporting one duck or one egg, adhering to the constraint that Janet can only carry one item (duck or egg) with her in the boat.


  • AI peddlers just love any “critique” that presumes the AI is great at something.

    Safety concern that LLMs would go Skynet? Say no more, I hear you and I’ll bring it up first thing in the Congress.

    Safety concern that terrorists might use it to make bombs? Say no more! I agree that the AI is so great for making bombs! We’ll restrict it to keep people safe!

    It sounds too horny, you say? Yeah, good point, I love it. Our technology is better than sex itself! We’ll keep it SFW to keep mankind from going extinct due to robosexuality!



  • The counting failure in general is even clearer and lacks the excuse of unfavorable tokenization. The AI hype would have you believe just an incremental improvement in multi-modality or scaffolding will overcome this, but I think they need to make more fundamental improvements to the entire architecture they are using.

    Yeah.

    I think the failure could be extremely fundamental - maybe local optimization of a highly parametrized model is fundamentally unable to properly learn counting (other than via memorization).

    After all there’s a very large number of ways how a highly parametrized model can do a good job of predicting the next token, which would not involve actual counting. What makes counting special vs memorization is that it is relatively compact representation, but there’s no reason for a neural network to favor compact representations.

    The “correct” counting may just be a very tiny local minimum, with tall hill all around it and no valley leading there. If that’s the case then local optimization will never find it.


  • I think you can make a slight improvement to Wolfram Alpha: using an LLM to translate natural language queries into queries WA can consume, then feeding them into WA. WA always reports exactly what it computed, so if it “misunderstands” you, it’s a lot easier to notice.

    The problem here is that AI boys got themselves hyped up for it being actually intelligent, so none of them would ever settle for some modest application of LLMs. Google fired the authors of “stochastic parrot” paper, AFAIK.

    simply pasting LLM output into CAS input and then the CAS output back into LLM input (which, let’s be honest, is the first thing tech bros will try as it doesn’t require much basic research improvement), will not help that much and will likely generate an entirely new breed of hilarious errors and bullshit (I like the term bullshit instead of hallucination, it captures the connotation errors are of a kind with the normal output).

    Yeah I have examples of that as well. I asked GPT4 at work to calculate the volume of 10cm long, 0.1mm diameter wire. It seems to be doing correct arithmetic by some mysterious means which do not use scientific notation, and then the LLM can not actually count so it miscounts zeroes and outputs a result that is 1000x larger than the correct answer.


  • Well the problem is it not having any reasoning period.

    Not clear what symbolic reasoning would entail, but puzzles generally require you to think through several approaches to solve them, too. That requires a world model, a search, etc. the kind of stuff that actual AIs, even a tik tac toe AI, have, but LLMs don’t.

    On top of it this all works through machine learning, which produces the resulting network weights through very gradual improvement at next word prediction, tiny step by tiny step. Even if some sort of discrete model (like say the account of what’s on either side of the river) could help it predict the next token, there isn’t a tiny fraction of a discrete “model” that would help it, and so it simply does not go down that path at all.



  • But if your response to the obvious misrepresentation that a chatbot is a person of ANY level of intelligence is to point out that it’s dumb you’ve already accepted the premise.

    How am I accepting the premise, though? I do call it an Absolute Imbecile, but that’s more of a word play on the “AI” moniker.

    What I do accept is an unfortunate fact that they did get their “AIs” to score very highly on various “reasoning” benchmarks (some of their own design), standardized tests, and so on and so forth. It works correctly across most simple variations, such as changing the numbers in a problem or the word order.

    They really did a very good job at faking reasoning. I feel that even though LLMs are complete bullshit, the sheer strength of that bullshit is easy to underestimate.





  • Other thing to add to this is that there’s just one or two people in the train providing service for hundreds of other people or millions of dollars worth of goods. Automating those people away is simply not economical, not even in terms of the headcount replaced vs headcount that has to be hired to maintain the automation software and hardware.

    Unless you’re a techbro, who deeply resents labor, someone who would rather hire 10 software engineers than 1 train driver.


  • Also, my thought on this is that since an LLM has no internal state with which to represent the state of the problem, it can’t ever actually solve any variation of the river crossing. Not even those that it “solves” correctly.

    If it outputs the correct sequence, inside your head the model of the problem will be in the solved state, but on the LLM’s side there’s just a sequence of steps that it wrote down, with those steps directly inhibiting production of another “Trip” token, until that crosses a threshold. There isn’t an inventory or even a count of items, there’s an unrelated number that weights for or against “Trip”.

    If we are to anthropomorphize it (which we shouldn’t, but anyway), it’s bullshitting up an answer and it gradually gets a feeling that it has bullshitted enough, which can happen at the right moment, or not.



  • I love the “criti-hype”. AI peddlers absolutely love any concerns that imply that the AI is really good at something.

    Safety concern that LLMs would go Skynet? Say no more, I hear you and I’ll bring it up in the congress!

    Safety concern that terrorists might use it to make bombs? Say no more! I agree that the AI is so great for making bombs! We’ll restrict it to keep people safe!

    Sexual roleplay? Yeah, good point, I love it. Our technology is better than sex itself! We’ll restrict it to keep mankind from falling into the sin of robosexuality and going extinct! I mean, of course, you can’t restrict something like that, but we’ll try, at least until we release a hornybot.

    But any concern about language modeling being fundamentally not the right tool for some job (Do you want to cite a paper or do you want to sample from the underlying probability distribution?), hey hey hows about we talk about the skynet thing instead?


  • It used to mean things like false positives in computer vision, where it is sort of appropriate: the AI is seeing something that’s not there.

    Then the machine translation people started misusing the term when their software mistranslated by adding something that was not present in the original text. They may have been already trying to be misleading with this term, because “hallucination” implies that the error happens when parsing the input text - which distracts from a very real concern about the possibility that what was added was being plagiarized from the training dataset (which carries risk of IP contamination).

    Now, what’s happening is that language models are very often a very wrong tool for the job. When you want to cite a court case as a precedent, you want a court case that actually existed - not a sample from the underlying probability distribution of possible court cases! LLM peddlers don’t want to ever admit that an LLM is the wrong tool for that job, so instead they pretend that it is the right tool that, alas, sometimes “hallucinates”.


  • YOU CAN DO THAT WITHOUT AI.

    Can they, though? Sure, in theory Google could hire millions of people to write overviews that are equally idiotic, but obviously that is not something they would actually do.

    I think there’s an underlying ethical theory at play here, which goes something like: it is fine to fill internet with half-plagiarized nonsense, as long as nobody dies, or at least, as long as Google can’t be culpable.