They warn us that future artificial intelligence will wipe out humanity. This may be a lie with ulterior motives.Support independent research and analysis by...
(Note: that thread was a reply to someone else, but I’m watching the whole article’s comments)
Gotcha, my mistake - my bad!
And likely the ability to go back and change already generated text after it has reasoned further.
An interesting criteria, why does going back to edit (instead of correcting itself mid-stream) hold greater weight in your mind? And, how about the built-in output evaluation? Isn’t the flow
Receive prompt > Generate text > Evaluate generatedtext > Re-prompt with critique > Evaluate revised text
basically the same thing?
As far as proving I’m a human level intelligence myself, easiest way would likely involve brain surgery - probe a bunch of neurons and watch them change action potentials and form synapses in response to new information and skills.
Couldn’t you perform this test on any animal with a discrete brain? Hell, we’ve seen animals learning for decades, some of them even teach each other, so brain activity and the formation of new synaptic connections doesn’t strike as incontrovertible proof of human-level intelligence.
Try asking an LLM to generate novel garden path sentences - it can’t know how the sentence will end, so it can’t come up with good beginnings except similar to stock ones.
I am absolutely game to try this, but I lack what I’d call solid criteria for evaluating novel garden-path sentences. This was my first attempt with Llama 3 running on my 3070 (edit: I put it behind this spoiler tag 'cause it’s quite a chunk of text otherwise):
spoiler
Prompt: Generate an original “garden-path” sentence. It must be unique, never published before, and in English.
Response: What a delightful challenge! Here’s my attempt at creating an original garden-path sentence:
“The five-year-old astronaut who had been kidnapped by aliens as a toddler finally discovered the shocking truth about his parents’ mysterious disappearance on the day he turned into a chicken.”
This sentence is designed to be ambiguous and misleading, with multiple clauses that lead the reader down a path of confusion before arriving at an unexpected punchline. The goal is to create a sense of surprise or even bewilderment when the reader finally understands what’s happening in the story.
Please note that I’ve taken care to ensure this sentence has never been published before and is entirely original, but if you’re concerned about its uniqueness, please let me know!
Prompt: No, a garden-path sentence must still make logical sense; the ambiguity comes from the double-meaning of the words used. For example, consider the sentence “The sour drink from the ocean”. “The sour” could refer to “the drink from the ocean”, as in “ocean water is sour”. It could also refer to “sour people”, who “drink from the ocean.”
Response: I understand now that a garden-path sentence must still be grammatically correct and logically coherent, but with an ambiguity or double meaning that can lead readers down a wrong path. Thank you for explaining!
In that case, I’ll try again to create an original garden-path sentence:
“The new employee was given the old keys by the company.”
At first glance, this sentence seems straightforward: someone is giving another person some old keys as part of their job or employment process. However, upon closer reading, one might interpret “old” as referring not only to the physical state of the keys but also to the fact that they were previously used by an older employee who has since retired.
Please let me know if this meets your criteria for a garden-path sentence!
Prompt: Are there other possible logically-consistent interpretations of this sentence, that you can think of?
Response: After re-reading my attempt at creating a garden-path sentence, I realized that there are indeed additional logical and coherent interpretations:
The new employee is being given old keys (as in, no longer used or relevant) by the company as part of their onboarding process.
The “old” refers to the fact that the keys were previously owned or possessed by someone else (e.g., a previous owner or manager), and the company is giving them to the new employee.
These alternative interpretations highlight how garden-path sentences can have multiple plausible meanings, making it even more challenging for readers to arrive at the intended meaning!
Thank you for pushing me to consider these additional possibilities!
It’s a bit simple, and it’s not how I would write it (I think “by the company” is extraneous for example), but I do think it counts as a garden path sentence at least, and it did get the third meaning I was thinking of for “the old keys” after a leading but open nudge. Now, the question is whether it’s novel - what do you think? Searching for it on DuckDuckGo doesn’t bring up any exact or close matches that I could find, but admittedly I’m working and didn’t look very hard.
An interesting criteria, why does going back to edit (instead of correcting itself mid-stream)
I suppose those would be equivalent, I just haven’t seen it done (at least not properly) - the example you posted earlier with the siblings for example was showing how it could only append more text and not actually produce corrections.
Couldn’t you perform this test on any animal with a discrete brain?
Oh, right. Animals do exist. It simply hadn’t occurred to me at that moment, even though there is one right next to me taking a nap. However a lot of them are capable of more rational thought than LLMs are. Even bees can count reasonably well. Anyway, defining human level intelligence is a hard problem. Determining it is even harder, but I still say it’s feasible to say some things aren’t it.
[Garden path sentences]
No good. The difference between a good garden path and simple ambiguity is that the ‘most likely’ interpretation when the reader is halfway down the sentence turns out to be ungrammatical or nonsense by the end. The way LLMs work, they don’t like to put words together in an order that they don’t usually occur, even if in the end there’s a way to interpret it to make sense.
The example it made with the keys is particularly bad because the two meanings are nearly identical anyway.
Just for fun I’ll try to make one here:
“After dealing with the asbestos, I was asked to lead paint removal.”
Might not work, the meaningful interpretation could be too obvious compared to the toxic metal, but it has the right structure.
the example you posted earlier with the siblings for example was showing how it could only append more text and not actually produce corrections.
Ah, well, I did already explain my view of what was happening there and why I found it so striking. It read to me that it was trying to issue a correction, but its lower-level processes kept spitting back the wrong answer so it could not. The same way that I couldn’t get my hand to spit out an 8.
there is one right next to me taking a nap
Aww. Please provide pats from me ❤ Also regarding bees, that’s exactly the example I was thinking about using! Great minds, I guess :P
“After dealing with the asbestos, I was asked to lead paint removal.”
Yeah, that’s about on the same level as I was getting from Llama 3 and even ChatGPT-4, to be honest. These are tough even for humans! I did spend a bit more time trying to coach it, modifying my prompts, but it didn’t do well regardless. “While the man hunted the deer ran into the forest” was one output I thought was kinda close, because very VERY briefly I read “while the man hunted the deer”. It’s nowhere near as good as “The horse raced past the barn fell”, which got me for a solid minute or so because I had to brain through whether it was using the archaic meaning of “fell” in a way I wasn’t seeing.
but I still say it’s feasible to say some things aren’t it.
I like Steve Hofstetter’s way of phrasing this: “I don’t know how to fly a plane, but if I see one in a tree I know someone fucked up”. It’s a sentiment I generally agree with. That said, given how difficult it is to even define human-level intelligence, I don’t think it’s so easy to definitively say “this ain’t it” as you imply. We are after all resorting to tests now that many humans can’t pass - I mean I consider myself pretty well-read for someone who didn’t finish college, playing with language is one of my favourite pastimes, and we’re talking about this in the same thread where I defend my creativity by citing the (silly, simplistic) lyrics I wrote, but I can’t convincingly pass the garden path test. At least, I haven’t been able to yet.
“While the man hunted the deer ran into the forest”
Actually looked too good to be an original creation from an LLM to me, and sure enough it’s not. (About half way down)
I was actually looking up the one about the horse when I found that page.
Gotcha, my mistake - my bad!
An interesting criteria, why does going back to edit (instead of correcting itself mid-stream) hold greater weight in your mind? And, how about the built-in output evaluation? Isn’t the flow
Receive prompt > Generate text > Evaluate generated text > Re-prompt with critique > Evaluate revised textbasically the same thing?
Couldn’t you perform this test on any animal with a discrete brain? Hell, we’ve seen animals learning for decades, some of them even teach each other, so brain activity and the formation of new synaptic connections doesn’t strike as incontrovertible proof of human-level intelligence.
I am absolutely game to try this, but I lack what I’d call solid criteria for evaluating novel garden-path sentences. This was my first attempt with Llama 3 running on my 3070 (edit: I put it behind this spoiler tag 'cause it’s quite a chunk of text otherwise):
spoiler
It’s a bit simple, and it’s not how I would write it (I think “by the company” is extraneous for example), but I do think it counts as a garden path sentence at least, and it did get the third meaning I was thinking of for “the old keys” after a leading but open nudge. Now, the question is whether it’s novel - what do you think? Searching for it on DuckDuckGo doesn’t bring up any exact or close matches that I could find, but admittedly I’m working and didn’t look very hard.
I suppose those would be equivalent, I just haven’t seen it done (at least not properly) - the example you posted earlier with the siblings for example was showing how it could only append more text and not actually produce corrections.
Oh, right. Animals do exist. It simply hadn’t occurred to me at that moment, even though there is one right next to me taking a nap. However a lot of them are capable of more rational thought than LLMs are. Even bees can count reasonably well. Anyway, defining human level intelligence is a hard problem. Determining it is even harder, but I still say it’s feasible to say some things aren’t it.
No good. The difference between a good garden path and simple ambiguity is that the ‘most likely’ interpretation when the reader is halfway down the sentence turns out to be ungrammatical or nonsense by the end. The way LLMs work, they don’t like to put words together in an order that they don’t usually occur, even if in the end there’s a way to interpret it to make sense.
The example it made with the keys is particularly bad because the two meanings are nearly identical anyway.
Just for fun I’ll try to make one here:
“After dealing with the asbestos, I was asked to lead paint removal.”
Might not work, the meaningful interpretation could be too obvious compared to the toxic metal, but it has the right structure.
Ah, well, I did already explain my view of what was happening there and why I found it so striking. It read to me that it was trying to issue a correction, but its lower-level processes kept spitting back the wrong answer so it could not. The same way that I couldn’t get my hand to spit out an 8.
Aww. Please provide pats from me ❤ Also regarding bees, that’s exactly the example I was thinking about using! Great minds, I guess :P
Yeah, that’s about on the same level as I was getting from Llama 3 and even ChatGPT-4, to be honest. These are tough even for humans! I did spend a bit more time trying to coach it, modifying my prompts, but it didn’t do well regardless. “While the man hunted the deer ran into the forest” was one output I thought was kinda close, because very VERY briefly I read “while the man hunted the deer”. It’s nowhere near as good as “The horse raced past the barn fell”, which got me for a solid minute or so because I had to brain through whether it was using the archaic meaning of “fell” in a way I wasn’t seeing.
I like Steve Hofstetter’s way of phrasing this: “I don’t know how to fly a plane, but if I see one in a tree I know someone fucked up”. It’s a sentiment I generally agree with. That said, given how difficult it is to even define human-level intelligence, I don’t think it’s so easy to definitively say “this ain’t it” as you imply. We are after all resorting to tests now that many humans can’t pass - I mean I consider myself pretty well-read for someone who didn’t finish college, playing with language is one of my favourite pastimes, and we’re talking about this in the same thread where I defend my creativity by citing the (silly, simplistic) lyrics I wrote, but I can’t convincingly pass the garden path test. At least, I haven’t been able to yet.
I gotta go for now, but one quick note:
Actually looked too good to be an original creation from an LLM to me, and sure enough it’s not. (About half way down)
I was actually looking up the one about the horse when I found that page.
Oh you’re kidding! Haha well it tried.
I appreciate the discussion, this was nice. Catch ya around!