Live data from Hacker News

Artificial neural networks are making strides towards consciousness?

economist.com

71–80 of 85 posts

Re: Artificial neural networks are making strides towards consciousness?

#71

Earlier quoted context omitted.

That was an intriguing suggestion. I found this GRE question: https://www.ets.org/gre/revised_general/prepare/verbal_reaso... . I'm kind of in a rush, so I picked some questions around Question 2 and gave them to OpenAI's chat bot. I reformulated the questions to make them not a multiple choice scenario. As far as the answer guide is concerned, it got the most obviously correct interpretation right, it also identifie…

Searching online for the following text: "AI: The passage addresses the issue of whether or not Glass's use of popular elements in his classical compositions makes him a composer of popular music." I find the following two pages both of which have text that looks similar to GPT-3's answer: https://www.ets.org/gre/revised_general/prepare/verbal_reaso... >> The passage describes in general terms how Philip Glass uses p…

"AI" is the tag used in OpenAI's chatbot, not the technology.

Hmm I wasn't making claims. I was interested in how the OpenAI's gpt-3 bot would do on a GRE question. Its a good question because it takes things out of their epistemological context and provides a more straightforward test. I think it would have gotten a 30%, so not good, though not terrible. I was not claiming the answers were original and I don't think I'm under a burden to prove something that I don't have an opinion on. The GRE itself does not ask for original responses, but instead to pick the correct answers from a list--that's part of why I thought it was an interesting exercise.

That said it piqued my interest, so I wrote an entirely original composition about a fictional composer and put it to the question. You will see how it correctly summarizes the text, but has trouble generalizing.

Human: There is a classical composer named Ron Johnson. Ron Johnson is well known for incorporating so-called gypsy music into his classical compositions. This practice has garnered criticism from several sources who believe his compositions are not "pure". There are also accusations of cultural appropriation. Nonetheless, the general critical consensus is that Johnson's music pays homage to and in fact successfully weaves Romani and classical tropes together into something wherein the whole is greater than the parts. There is one famous critic, though, who believes Johnson's work is terrible. This famousness of this critic leads the general public to believe Johnson is terrible. The passage addresses what issue related to Johnson's use of musical sources for his classical compositions?

AI: The passage addresses the issue of whether Ron Johnson's use of gypsy music in his classical compositions amounts to cultural appropriation.

Human: If someone hears Johnson's music, what do they usually think?

AI: People usually think that Ron Johnson's music is either good or bad based on the opinion of the famous critic.

Human: What would Romani people think of Ron Johnson's music?

AI: Romani people would likely think that Ron Johnson's music is successful in paying homage to and weaving together Romani and classical tropes into something wherein the whole is greater than the parts.

Human: What does the average person think about Ron Johnson's music?

AI: The average person is likely to think that Ron Johnson's music is either good or bad based on the opinion of the famous critic.

Human: Who has criticized Johnson's music?

AI: The famous critic has criticized Johnson's music.

Human: What does Johnson appropriate?

AI: Johnson is accused of appropriating Romani music in his classical compositions.

Human: Does the passage suggest Ron Johnson is a great composer?

AI: No, the passage does not explicitly suggest that Ron Johnson is a great composer. However, it does suggest that he is successful in weaving Romani and classical music together into something new and unique, which has been praised by many critics.

Human: Does the passage suggest Ron Johnson is a derivative composer?

AI: No, the passage does not explicitly suggest that Ron Johnson is a derivative composer. However, it does suggest that he is successful in weaving Romani and classical music together into something new and unique, which has been praised by many critics.

Human: Does the passage suggest Ron Johnson is successful at weaving the music together?

AI: Yes, the passage suggests that Ron Johnson is successful at weaving Romani and classical music together, and that this has been praised by many critics.

Human: Does the famous critic unfairly influence the public?

AI: The famous critic's opinion may unfairly influence the public's perception of Ron Johnson's work.

Human: Does the famous critic fairly influence the public?

AI: There is no easy answer to this question. On the one hand, it could be argued that the famous critic's opinion carries a lot of weight and can therefore unfairly influence the public's perception of Johnson's work. On the other hand, it could also be argued that the public is entitled to its own opinion and that the critic's opinion is just one among many. Ultimately, it is up to each individual to decide whether or not they believe the famous critic's opinion is fair.

Re: Artificial neural networks are making strides towards consciousness?

#72

Earlier quoted context omitted.

>I don’t see how consciousness is at all hard to define. A system that is aware of itself. A thermostat that is aware of the temperature inside its own housing is "aware of itself". It's not conscious however. Nailing down exactly what consciousness means is remarkably difficult.

Honestly I think this is largely because humans want the conclusion that only they are consious, or at least that only they and some animals are, and are trying really hard to carve out a definition that makes that work. Why would we do that? Well obviously because we create AI to do work for us and we don't want to have any ethical considerations get in the way of treating our new slaves however we want.

Yup this is my thinking also. It isn’t a hard concept imo people just like theologizing about why they’re special

Re: Artificial neural networks are making strides towards consciousness?

#73

Earlier quoted context omitted.

Consciousness means you know you exist. This is a super simple definition and GPT does not, nor do any of these AI models, meet this very simple definition.

my program that prints "hello world" to the screen is then conscious?

Does it make a convincing case?

Re: Artificial neural networks are making strides towards consciousness?

#74

Ugh. You can’t say “strides towards consciousness” until you define consciousness AND have a metric that can provide objective measure of such things.

By your logic, it would be wrong to say that OpenAI is closer to consciousness than a piece of lumber.

However, your comment is a good reminder that non-rigid thought patterns are not a prerequisite for consciousness. (How apropos your username!)

Re: Artificial neural networks are making strides towards consciousness?

#75
post #50

Earlier quoted context omitted.

https://archive.ph/5QS7t -- > [Hofstadter: ] I am at present very sceptical that there is any consciousness in neural-net architectures such as, say, GPT-3, despite the plausible-sounding prose it churns out at the drop of a hat. Let me explain my viewpoint through a few examples. // My colleague David Bender and I have recently enjoyed inventing all sorts of amusing probes of GPT-3 that reveal a mind-boggling hollow…

What this shows us is that GPT-3 doesn't really understand what it is talking about and is just a decently good bullshitter. To be frank, I've met humans with the same quality of always speaking with confidence about things they have no understanding of. Possibly this is a result of how the system is constructed, GPT-3 being forced to answer but not able to express uncertainty, for instance. At any rate I do not beli…

> I've met humans with the same quality of always speaking with confidence

You should have met some devoid of any expected key for understanding, for that matter. But if they had read the whole of the available encyclopedias, it would be interesting neurologically (à la Oliver Sacks) what determines their pseudorandom nonsense. Not paramount, just potentially interesting.

Although, surely, that reinforces the perception of one lacking in below said "operational description of Intelligence": that held ideas are criticized.

> is not, in some way

At this stage, I would prefer that first we achieve the milestone of "Intelligent", operationally described many times and practically meaning "something that makes it worth to listen to what you output", before going into more difficult areas.

Re: Artificial neural networks are making strides towards consciousness?

#76
post #66
post #3

>In our conversation, lamda tells me what it believes Ramesh felt that Lucy learned about what Mateo thought about Lucy’s overture. This is high order social modelling. I am not sure the example convinces me that what GPT-3 is doing here is 'modeling' the agents in the story. It feels like the author is trying to draw a contrast between rote statistical language modeling and higher-order understanding, and it's not c…

A model is not required to get everything right. I found those deductions absolutely amazing honestly.

It depends on your goal.

"Given the acquired studies in astronomy and rocket science, engineering and robotics, surely we can plan a mission to explore the solar corona in-place, which we calculated as safe and achievable, provided we limit the physical environmental constraints by carrying the mission on rigorously at nighttime"

Maybe you are into entertainment, maybe you are into AI (AKA "automated problem solving").

Maybe the appearance of some emergent property leads to potential foundations, maybe just to potential for deception.

It is very dangerous to have around hollow simulacra "good at faking it" (from pseudo-professionalism to populism, etc).

Re: Artificial neural networks are making strides towards consciousness?

#77

Ugh. You can’t say “strides towards consciousness” until you define consciousness AND have a metric that can provide objective measure of such things.

"My infant child is making strides toward consciousness" Completely uncontroversial, yet we don't have a metric and we haven't defined it precisely.

I and many others strongly disagree with the statement’s assumption that infants are not conscious, so it’s not a completely uncontroversial statement. Sure, they have very limited I/O, but I understand that as orthagonal to consciousness.

Re: Artificial neural networks are making strides towards consciousness?

#78

Earlier quoted context omitted.

"My infant child is making strides toward consciousness" Completely uncontroversial, yet we don't have a metric and we haven't defined it precisely.

I and many others strongly disagree with the statement’s assumption that infants are not conscious, so it’s not a completely uncontroversial statement. Sure, they have very limited I/O, but I understand that as orthagonal to consciousness.

Replace "infant" with fetus then...

Re: Artificial neural networks are making strides towards consciousness?

#79

Earlier quoted context omitted.

I and many others strongly disagree with the statement’s assumption that infants are not conscious, so it’s not a completely uncontroversial statement. Sure, they have very limited I/O, but I understand that as orthagonal to consciousness.

Replace "infant" with fetus then...

Still not uncontroversial: https://pubmed.ncbi.nlm.nih.gov/31922622/

Re: Artificial neural networks are making strides towards consciousness?

#80

Earlier quoted context omitted.

Replace "infant" with fetus then...

Still not uncontroversial: https://pubmed.ncbi.nlm.nih.gov/31922622/

It's obviously not controversial. Your linked article doesn't claim that a 0-week old Fetus is conscious. It claims you can define consciousness in such a way that a 24 week old fetus is conscious. That 100% completely reinforces my point, which is that we are in agreement that a 0-week fetus moves toward consciousness (your article claims it achieves it by 24 weeks). We are able to agree on that without agreeing on the definition of consciousness, so the lack of a unanimous definition doesn't prevent us from pointing at AI and saying "this is moving toward consciousness".
Post reply on HN