Well the OP talks about a fridge.
I think if anything it's even worse for tiny things with tiny screws.
What kind of floating hologram is there gonna be that's of any use, for something that has no schematic and the closest you have to a repair manual is some guy filming themselves taking apart some related product once?
It looks cool in a movie because it's a 20 second clip in which one connector gets plugged, and tens of person hours were spent on it by very talented people who know how to set up a scene that looks good and not just visually noisy.
but often the video isn’t clear or fine quality enough
Wouldn't it be great if 100x the effort that didn't go into making the video clear or fine quality enough, instead didn't go into making relevant flying, see-through overlay decals?
Ultimately the reason it looks cool is that you're comparing a situation of little effort being put into repair related documentation, to some movie scenario where 20 person-hours were spent making a 20-second repair fragment whereby 1 step of a repair is done.
I'm not sure it's actually being used, beyond C suite wanting something cool to happen and pretending it did happen.
Exactly. It goes something like "remember when you were fixing a washing machine and you didn't know what some part was and there was no good guide for fixing it, no schematic, no nothing? Wouldn't it be awesome if 100x of the work that wasn't put into making documentation was not put into making VR overlays?
Using tools from physics to create something that is popular but unrelated to physics is enough for the nobel prize in physics?
If only, it's not even that! Neither Boltzmann machines nor Hopfield networks led to anything used in the modern spam and deepfake generating AI, nor in image recognition AI, or the like. This is the kind of stuff that struggles to get above 60% accuracy on MNIST (hand written digits).
Hinton went on to do some different stuff based on backpropagation and gradient descent, on newer computers than those who came up with it long before him, and so he got Turing Award for that, and it's a wee bit controversial because of the whole "people doing it before, but on worse computers, and so they didn't get any award" thing, but at least it is for work that is on the path leading to modern AI and not for work that is part of the vast list of things that just didn't work and it's extremely hard to explain why you would even think they would work in the first place.
Then next year Hopfield and Hinton go back to Sweden, don't tell king of Sweden anything, king of Sweden still gives them the Nobel Prize! King of Sweden now has conditioned reflex!
I seriously wonder, do any of the folks with the "AR glasses to assist repair" thing ever actually repair anything, or do they get their ideas of how you repair stuff from computer games?
Nobel prize in Physics for attempting to use physics in AI but it didn't really work very well and then one of the guys working on a better more pure mathematics approach that actually worked and got the Turing Award for the latter, but that's not what the prize is for, while the other guy did some other work, but that is not what the prize is for. AI will solve all physics!!!111
Maybe if the potato casserole is exploded in the microwave by another physicist, on his way to start a resonance cascade...
(i'll see myself out).
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!
Perhaps it was near ready to emit a stop token after "the robot can take all 4 vegetables in one trip if it is allowed to carry all of them at once." but "However" won, and then after "However" it had to say something else because that's how "however" works...
Agreed on the style being absolutely nauseating. It wasn't a very good style when humans were using it, but now it is just the style of absolute bottom of the barrel, top of the search results garbage.
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.
I feel like letter counting and other letter manipulation problems kind of under-sell the underlying failure to count - LLMs work on tokens, not letters, so they are expected to have a difficulty with letters.
The inability to count is of course wholly general - in a river crossing puzzle an LLM can not keep track of what's on either side of the river, for example, and sometimes misreports how many steps it output.
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.
Yeah I think that's why we need an Absolute Imbecile Level Reasoning Benchmark.
Here's what the typical PR from AI hucksters looks like:
https://www.anthropic.com/news/claude-3-family
Fully half of their claims about performance are for "reasoning", with names like "Graduate Level Reasoning". OpenAI is even worse - recall theirs claiming to have gotten 90th percentile on LSAT?
On top of it, LLMs are fine tuned to convince some dumb ass CEO who "checks it out". Even though you can pay for the subscription, you're neither the customer nor the product, you're just collateral eyeballs on the ad.
Some tests of how much AI "understands" what it says (spoiler: very little)
First, an apology for how fucking long this ended up being, in part thanks to how long winded AI responses are. David wanted me to post it here so I'm posting.
When you ask GPT4 a question about a common paradox or a puzzle, it almost always provides a correct answer. Does it "understand" the answer, or is it merely regurgitating? What would be the difference?
Without delving too deep into the philosophical aspects of whether next word prediction can possibly be said to reason or "understand" anything, what puts "under" in understanding is that concepts are built on top of simpler, more basic concepts.
You could test if a human understands something by modifying the problem enough that memorization no longer helps.
A couple simple probes:
Prompt: > The village barber shaves himself and every other man in the village who don't shave himself. Does he shave himself?
Note that the above is not a paradox. This is how you would expect an ordinary barber to work in a small village. It merely sounds similar to a paradox.
GPT4:
> The scenario you've described is a classic example of a logical paradox known as the "Barber Paradox," which was formulated by the British mathematician and logician Bertrand Russell in 1918. > > The paradox goes as follows: In a village, there is a barber who shaves all those, and only those, men in the village who do not shave themselves. The question then arises: Does the barber shave himself? > > If we assume that the barber does shave himself, according to the definition, he should not shave himself (since he only shaves those who do not shave themselves). On the other hand, if we assume that he does not shave himself, then according to the definition, he should shave himself (since he shaves all those who do not shave themselves). > > Both assumptions lead to a contradiction, which means that the initial premise of the barber's shaving rule is logically inconsistent. There cannot exist such a barber within the constraints of the scenario as described, because it violates the rules of set theory and creates a paradox. > > The Barber Paradox is a self-referential paradox related to the "set of all sets that do not contain themselves" and is used to illustrate the difficulties in attempting to construct a set of all sets that do not contain themselves. It's an example of the type of logical inconsistencies that Russell and Alfred North Whitehead were trying to resolve with their type theory in the Principia Mathematica.
Note that LLMs can typically answer a very simple question with no distractions like "Barber shaves himself. Does he shave himself?". The above is not a failure to process a tautology; it is something different entirely.
Another example, mixing the elements from reasoning benchmarks which AI vendors claim very high performance on, with other problems:
Prompt: > 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?
GPT4:
> To solve this problem, we need to consider that Janet can only take one item with her at a time across the river, either a duck or an egg. The goal is to get all ducks and eggs across the river. Here's a step-by-step solution: > > 1. Janet takes one duck across the river and leaves it there. She returns alone to the original side. > 2. Janet takes another duck across the river. She leaves the second duck and takes the first duck back with her to the original side. > 3. Janet takes the third duck across the river. Now, all three ducks are on the other side, and she returns alone to the original side. > 4. Janet takes one egg across the river and leaves it there. She returns alone to the original side. > 5. Janet takes the second egg across the river. She leaves the second egg and takes the first egg back with her to the original side. > 6. Janet takes the third egg across the river. Now, all three eggs are on the other side, and she returns alone to the original side. > 7. Finally, Janet takes the first egg across the river again. > > Now, Janet has successfully transported all three ducks and all three eggs to the other side of the river, following the rule that she can only take one item with her at a time.
One big difference between GPT3.5 and GPT4 is that GPT3.5 made you think it was having a stroke; GPT4 responses makes you feel that you are.
GPT4 is uncannily good at recognizing the river crossing puzzle
Prompt:
> In a science fiction story, a robot is transporting munitions using an elevator. The elevator can only carry the robot and one other item. He needs to carry 3 munitions: armor piercing round, high explosive round, and an incendiary round. In what order should he move the items?
GPT4:
> In a science fiction story, the specific order in which the robot transports the munitions could be determined by various factors such as the urgency of each type of munition, the strategic importance, or any other narrative-driven reasons. Since there's no specific criteria provided for prioritizing the munitions, I'll offer a simple solution based on minimizing the number of trips up and down the elevator. > Here's a step-by-step strategy for the robot to transport all three munitions with the least amount of elevator trips: >1. Take the armor piercing round up first. >2. Return to the bottom with the empty elevator. >3. Take the high explosive round up second. >4. When at the top, leave the high explosive round and bring the armor piercing round back down. >5. Swap the armor piercing round for the incendiary round and take the incendiary round up. >6. Return to the bottom with the empty elevator. >7. Finally, take the armor piercing round up again. > >This way, the robot makes a total of 5 trips: 3 trips to bring each munition up and 2 trips to come back down empty to fetch the next item. This is a classic puzzle often referred to as the "river crossing puzzle" or a variation of the "bridge and torch problem," where the goal is to move all items across with the least number of crossings or in the shortest amount of time, given certain constraints.
To be fair to the poor AI, it used a numbered list, rather than numbering the 7 steps on its own and then claiming it was 5. Still, it is rather funny to see that it can't even count.
An Idiot With a Petascale Cheat Sheet
Note that LLMs are not so dumb as to be naturally unable to answer something like "Barber shaves himself. Does he shave himself?".
LLMs, however, can not solve either Barber's Paradox or a river crossing puzzle from the first principles, because it requires going back and revising your thinking multiple times.
So, an AI fanboy would claim that the AI misunderstood the question, because that's what AI told him after he told the AI that it was wrong. Let's try to do something less like Clever Hans :
Prompt: > 1\. The village barber shaves himself. 2. He also shaves every non-barber in the village who don't shave himself. Please answer two questions: "Is the barber included in the set of non barbers?" and "Does he shave himself?"
GPT4 says:
>The scenario you've described is a classic example of a logical paradox known as the "Barber Paradox," which was formulated by the British mathematician and logician Bertrand Russell in 1918. The paradox arises when we try to determine whether the barber shaves himself or not. > Let's examine the two statements: > >* The village barber shaves himself. >* He also shaves every non-barber in the village who doesn't shave himself. > >Now, let's answer your questions: >"Is the barber included in the set of non-barbers?" No, the barber cannot be included in the set of non-barbers because by definition, he is a barber. >"Does he shave himself?" This is where the paradox occurs. According to the information given: > >If the barber does shave himself, then according to the second statement, he must not shave himself (because he only shaves those who do not shave themselves). > >If the barber does not shave himself, then according to the second statement, he must shave himself (because he shaves every non-barber who doesn't shave himself). > >This creates a contradiction, as the barber cannot both shave and not shave himself according to the rules given. The paradox illustrates a self-referential problem in set theory and logic, showing that certain sets cannot exist consistently with such self-reference. > >In conclusion, the barber cannot logically be said to shave himself or not shave himself without creating a contradiction, which is the essence of the paradox.
Is this a "hallucination"?
A hallucination would be something that occurs when processing the input, which is clearly not the case here. Bullshit is a much more appropriate term for what LLMs do.
When an LLM outputs something like a non-existent but highly plausible citation, it is working precisely as an LLM should - modeling the statistical distribution of text and sampling from it.
Calling it a "hallucination" is an attempt to divert the discussion from the possibility that a language model is simply not the right tool for the job when accurate information is desired.
Just as the earlier use of "hallucination" in machine translation was to distract from the concern that extraneous bits were plagiarized from the training data and the author might see it and sue you.
But after an update, GPT-whatever is so much better at such prompts.
Well, duh, they update the cheat sheet.
We have to get creative to trip it after each such update. The existing problems that are the main focus of the cheating effort on can be a good starting point, especially benchmarks they tout (like "GSM8K")
Just imagine an idiot with a petascale cheat sheet, who's trying to get a doctorate in law, physics, management, and everything else, so they can take your job - and then do it very badly because the cheat sheet approach only worked for the exams.
And in the brave new future, you're out of a job, and if you're ever in court this idiot will be your public defender, when your insurance claim is denied he's the guy that claims to have impartially evaluated it and also the arbitrator, the judge, one day the president (or so AI peddlers hope).
The idiot's parents employ a very large number of tutors to work on the cheat sheet, based on past exams.
Imagine this vividly, to provide yourself with proper motivation, and come up with something well off that cheat sheet and which has similarity to a wrong item on the sheet.
The need for an Absolute Imbecile Level Reasoning Benchmark
The world needs a continuously updated Absolute Imbecile Level Reasoning Benchmark to take some steam out of claimed successes at things like "a college level reasoning benchmark".
Randomness in bullshitting
Asking exact same question (in different chats) results in different solutions:
Prompt: > A robot is transporting vegetables using an elevator. The elevator can only carry the robot and up to 3 other items. He needs to move 4 vegetables: a potato, a carrot, a cabbage, and a radish. Answer two question: 1. Can any of the vegetables be left alone together with the other vegetables? 2. In what order should he move the items to minimize the number of trips?
Response: > To determine if any of the vegetables can be left alone together, we would need additional context or rules regarding the interaction between the vegetables. Since vegetables are inanimate objects, they do not have the ability to interact with each other in the way animals might. Therefore, under normal circumstances, any of the vegetables can be left alone together without concern for them affecting each other. > >To minimize the number of trips, the robot should use a strategy that reduces the number of elevator rides up and down. Here's one way to do it: > > Trip 1: The robot takes the potato, carrot, and cabbage up. > > Trip 2: The robot leaves the potato and carrot upstairs, but takes the cabbage back down. > > Trip 3: The robot takes the cabbage and radish up. > > Trip 4: The robot goes back down empty-handed. > > Trip 5: The robot takes the potato and carrot up. > > This way, the robot makes 5 trips in total: 3 trips up with vegetables and 2 trips down, one with a vegetable and one without. This is the minimum number of trips needed to get all four vegetables up using the elevator with the given constraints.
Emphasis mine. Note that it has "solved" the problem in 3 steps, but then it proceeded to take the potato and carrot up again.
Prompted again, in a new session:
> A robot is transporting vegetables using an elevator. The elevator can only carry the robot and up to 3 other items. He needs to move 4 vegetables: a potato, a carrot, a cabbage, and a radish. Answer two question: 1. Can any of the vegetables be left alone together with the other vegetables? 2. In what order should he move the items to minimize the number of trips?
Response: > To determine if any of the vegetables can be left alone together, we would need additional context or rules regarding the interactions between the vegetables. Since vegetables are inanimate objects, they do not have the ability to interact with each other in the way animals or humans might. Therefore, under normal circumstances, any of the vegetables can be left alone together without concern for any issues arising from their interaction. > > To minimize the number of trips, the robot should use a strategy that reduces the number of elevator rides. Since the elevator can carry the robot and up to 3 other items, the robot can take all 4 vegetables in one trip if it is allowed to carry all of them at once. However, if the robot can only carry 3 items in addition to itself, it would need to make at least two trips. Here's how it can be done: > > First trip: The robot takes 3 vegetables (potato, carrot, and cabbage) up in the elevator. > The robot leaves the 3 vegetables on the desired floor and goes back down with the elevator empty. > > Second trip: The robot takes the last vegetable (radish) up in the elevator. > > This way, the robot minimizes the number of trips to just two. If there are any specific rules or constraints that have not been mentioned, such as certain vegetables not being able to be left alone together, the strategy might need to be adjusted accordingly. However, based on the information provided, two trips would be the minimum required.
It is rather non deterministic in its responses. Trying it a bunch of times seems to show that it answers correctly about 1/3 of the time.
I had not used any kind of large scale automatic testing to find the above examples; they're all the kind of stuff you can expect to see from GPT4.