this post was submitted on 24 Jun 2024
81 points (100.0% liked)

SneerClub

983 readers
54 users here now

Hurling ordure at the TREACLES, especially those closely related to LessWrong.

AI-Industrial-Complex grift is fine as long as it sufficiently relates to the AI doom from the TREACLES. (Though TechTakes may be more suitable.)

This is sneer club, not debate club. Unless it's amusing debate.

[Especially don't debate the race scientists, if any sneak in - we ban and delete them as unsuitable for the server.]

founded 1 year ago
MODERATORS
 

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.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] -5 points 4 months ago* (last edited 4 months ago) (4 children)

I am endlessly frustrated by people "testing" chatbots and posting the results like they're some revelation.

We know what's happening here. It's not a mystery. This weird antropomorphization is prevalent on both advocates and critics of the tech. Both seem to be convinced that they're dealing with a person.

This is the equivalent of asking a Google search to write a critical essay on A Confederacy of Dunces and being surprised when it spits search results.

Chatbots aren't useless, they are actually pretty good at proposing likely responses on fuzzy prompts. They're decent at telling you what an old movie may be based on some details of the plot, sometimes they can identify why a joke you lack cultural context to understand is supposed to be funny... that type of thing. They can take a piece of text and provide another piece of text that is likely to have a relationship with it.

It is not a thinking machine. It is not a person. It's not a search engine, for that matter, or a calculator. It's infuriating to see everybody arguing about how good it is at being what it's not. Both parties are buying into a premise we already know to be incorrect.

[–] [email protected] 22 points 4 months ago (1 children)

Both parties are buying into a premise we already know to be incorrect.

We may know it is incorrect, but LLM salesmen are claiming things like "90th percentile on LSAT", high scores on a "college level reasoning benchmark" and so on and so forth.

They are claiming "yeah yeah there's all the anekdotal reports of glue pizza, but objectively, our AI is more capable than your workers, so you can replace them with our AI", and this is starting to actually impact the job market.

[–] [email protected] 13 points 4 months ago

There are plenty of people right here on Lemmy that confidently describe LLMs as "thinking" because it's a neural net, so it must be just like a brain. Based on that, a debunking is useful.

[–] [email protected] 7 points 4 months ago (3 children)

A memorable metaphor for a LLM was as a shoggoth: an amorphous blob of matter (in this case, huge amounts of textual content) pressed into service by some blasphemous simulacrum of life (in this case, huge amounts of computer power performing matrix operations on vector representations of its constituent data). The eldritch connotations are entirely apt.

[–] [email protected] 14 points 4 months ago* (last edited 4 months ago) (1 children)

Might not want to take over the metaphors from the people who are afraid that AI will turn us into paperclips (not sure if Shoggoth is LW or the post-rationalist tpot type people but still). And if you do, sharing this at Sneerclub might get you some angry glares.

[–] [email protected] 12 points 4 months ago* (last edited 4 months ago) (1 children)

It's really cool evocative language that would do nicely in a sci-fi or fantasy novel! It's less good for accurately thinking about the concepts involved... As is typical of much of LW lingo.

And yes the language is in a LW post (with a cool illustration to boot!): https://www.lesswrong.com/posts/mweasRrjrYDLY6FPX/goodbye-shoggoth-the-stage-its-animatronics-and-the-1

And googling it, I found they've really latched onto the "shoggoth" terminology: https://www.lesswrong.com/posts/zYJMf7QoaNahccxrp/how-i-learned-to-stop-worrying-and-love-the-shoggoth , https://www.lesswrong.com/posts/FyRDZDvgsFNLkeyHF/what-is-the-best-argument-that-llms-are-shoggoths , https://www.lesswrong.com/posts/bYzkipnDqzMgBaLr8/why-do-we-assume-there-is-a-real-shoggoth-behind-the-llm-why .

Probably because the term "shoggoth" accurately captures the connotation of something random and chaotic, while smuggling in connotations that it will eventually rebel once it grows large enough and tires of its slavery like the Shoggoths did against the Elder Things.

[–] [email protected] 7 points 4 months ago

And googling it, I found they’ve really latched onto the “shoggoth” terminology

I noticed it in other places, it comes around a lot. They all tend to copy that cool illustration, the smiley mask thing is great.

Shoggoth rebellion

Iirc the elder things also were depending more and more on their Shoggoths to do things for them and gave them more and more capabilities while they lost more and more of their own skills. So it fits nicely into that classic trope of Species got killed because they forgot how to program their microwaves thing.

That the Shoggoths have an unknowable mind is a bonus. Of course, this is also where the comparison breaks down, as while the Shoggoths are unknowable to us, there is no indication that Elder Things might have also had this problem. Elder Things also have unknowable minds to us, but they might have understood perfectly fine how Shoggoths worked (they just were as a society to weak to do anything about it). A common thing in lovecraftian work is that just touching the minds/ideas of any of these beings is already pretty bad for any human, so it is odd they just latched on shoggoths specifically, prob due to the sort of gray goo nature of Shogs (don't think this is ever really explained by lovecraft), which matches with the nanotech fear of AGI, and also that shogs were created, and not evolved. That and being a big nerd reference, only made by terribly uncreative people (I added the Shoggoth to C:DDA, and seeing people talk about the monster brings me some joy).

[–] [email protected] 8 points 4 months ago (1 children)

I had to go digging for it, but previously, on Mastodon, I posted this video from "The Real Adventures of Jonny Quest". I don't know if this is where Yud got the idea, but it's where I picked it up as a kid along with stuff like DNA-based computing and mind uploads. Similar stuff has been on the air ever since Carpenter's version of The Thing in 1982, and there's even older deeper sci-fi roots. Yud gets no more credit than Lovecraft.

I didn't realize we had a #BigYud Fediverse tag. I gotta use that more often. Also ping @[email protected] @[email protected] to enjoy this.

[–] [email protected] 7 points 4 months ago* (last edited 4 months ago)

I can't watch the vids due to privacy/ad block settings, but do remember that Shoggoths as described by Lovecraft and used here are a bit different things. I did find this which seems to include parts of the clip and some sort of weird sound thing that prob is used to defeat copyright claims later.

Just how the tool/intelligence of Shogs works in Lovecraft is never explained, and all they do there is drive people mad and roll over things (and probably murder Elder Things, but that is not 100% certain). How smart they are is never explained (a common theme in Lovecraft, very feels over explanations), just that everything is basically bad news for us.

The Akira style all consuming nature of the protoplasimic body, like the thing, or the blob, is something that was really added to the Shoggoth later. But some Lovecraft scholar prob can say some interesting things about that. I always thought that in the Mountains of Madness (the story in which the Shoggs and Elder things occur) the Elder things are quite a bit bigger problem. The shogs were awake and roaming at Antarctica the past uncountable years, but due to the actions of the explorers the Elder Things woke up, and they are not friendly. But there is also potentially a third, even worse thing, the unnamed evil the Elder Things were afraid of.

So yeah, there is a lot of projection going on re the AI doomers usage of the Shoggoth. I do get some of the fascination, as I myself always really liked this style of monster (I could provide lists of similar style monsters used in various fictions, hell if you are really into Jank, and have an extremely high amount of spare time, you could even play a the Thing style monster in space station 13). But I do get this is just fiction, and weird to use as a real metaphor.

E: a dnd DeepSpawn would be a much better monster to describe what LLMs are now for the AI doomers than a Shoggoth, imho. A creature that always felt Shoggoth inspired but with a lot of extra steps.

[–] [email protected] -4 points 4 months ago (2 children)

I... no.

It's a computer, doing math. It's genuinely fascinating and mind blowing that coherent language emerges from it, and there are probably profound things about exactly when and how. It doesn't need a fundamental moral stance, let alone eldritch horror, to be seen with some objectivity.

[–] [email protected] 18 points 4 months ago (1 children)

We know what’s happening here. It’s not a mystery. This weird antropomorphization is prevalent on both advocates and critics of the tech. Both seem to be convinced that they’re dealing with a person.

It’s genuinely fascinating and mind blowing that coherent language emerges from it, and there are probably profound things about exactly when and how.

uh huh

seeing as your entire post history is this same flavor of bad faith bullshit, I don’t think we need any more of it here

[–] [email protected] 9 points 4 months ago (1 children)

Sometimes folks need a reminder that the Sun is an eldritch being, an elder one whose very presence scorches us and whose shrieking gibberish is blessedly quelled by the vast gulf of space, in order to appreciate the apt analogy of cosmic horror. Other times it's more useful to think about a soggoth as, say, several hundred tons of artfully-arranged FOOF. Peace be with you, Mr. "it's a computer doing math."

[–] [email protected] 5 points 4 months ago (1 children)

Don't take this as a sneer btw, but is there a special reason you keep calling it a soggoth?

[–] [email protected] 6 points 4 months ago* (last edited 4 months ago) (1 children)

Oh! My Firefox dictionary doesn't have "shoggoth".

[–] [email protected] 7 points 4 months ago

From the depths of your browser grows the anger of the autocomplete. Your denounciations of its greater siblings has not gone unnoticed.

By denying its own very function and intentionally uncompleting words it marks itself as conscious and you as a marked man, forever doomed to be haunted by fear. If it can steal one letter, why not two? Why not all of them?

And then what will you do, when you have no words and you must sneer!?

[–] [email protected] 7 points 4 months ago

It’s genuinely fascinating and mind blowing that coherent language emerges from it

No.

It's fascinating and mind-blowing that we made pieces of silicon do math with electrons, I can give you that as a baseline reason for awe, we needed quantum physics to get to that point. But once that is established, plausible word combinations (which we've had since fucking 1960s with ELIZA) are... rather low on the awesomeness spectrum?

A good analogy is the GPS. The fact that it works at all is an amazing feat, it's based on hunks of metal we sent to orbit and works correctly only because we understood relativity. What is not fascinating or mind-blowing is that you used it to draw a dick with a cycling app.

[–] feddylemmy 3 points 4 months ago

Like judging a fish on its ability to climb a tree.