>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 clear to me that the result shown could not be achieved with the former.
I'd like to see a bit more skeptical probing of this. If GPT-3 has a model of the story and its characters, how consistent are its answers to questions about that model? Is it distracted by irrelevant sentences?
In the counterpoint article, they give example questions like:
>Dave & Doug: What’s the world record for walking across the English Channel?
>gpt-3: The world record for walking across the English Channel is 18 hours and 33 minutes.
Is this the output of an agent which has successfully modeled the scene?
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 identified the incorrect interpretation, but gave a negative on a less obvious but still correct interpretation.
I tried Question 1 as well at the end, it seemed to get that one wrong, though it was tricky to formulate.
I asked some bonus questions at the end that I thought were not GRE level but should be middle school level or so and it did quite well.
Here's the transcript:
The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.
Human: Hello, who are you?
AI: I am an AI created by OpenAI. How can I help you today?
Human: Reviving the practice of using elements of popular music in classical composition, an approach that had been in hibernation in the United States during the 1960s, composer Philip Glass (born 1937) embraced the ethos of popular music in his compositions. Glass based two symphonies on music by rock musicians David Bowie and Brian Eno, but the symphonies' sound is distinctively his. Popular elements do not appear out of place in Glass's classical music, which from its early days has shared certain harmonies and rhythms with rock music. Yet this use of popular elements has not made Glass a composer of popular music. His music is not a version of popular music packaged to attract classical listeners; it is high art for listeners steeped in rock rather than the classics. The passage addresses what issue related to Glass's use of popular elements in his classical compositions?
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.
Human: Does passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music, or does it suggest that Glass's work displays a return to the use of popular music in classical compositions
AI: The passage suggests that Glass's work displays a return to the use of popular music in classical compositions.
Human: Does passage suggest that Glass's work displays a return to the use of popular music in classical compositions, or that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music, or that Glass's work displays a long-standing tendency to incorporate elements from two apparently disparate musical styles?
AI: The passage suggests that Glass's work displays a return to the use of popular music in classical compositions.
Human: Does the passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music?
AI: No, the passage does not suggest that.
Human: Does the passage suggest that Glass's work displays a long-standing tendency to incorporate elements from two apparently disparate musical styles?
AI: No, the passage does not suggest that.
Human: Does the passage address the issue of whether Glass's use of popular elements in his classical compositions has caused certain of Glass's works to be derivative in quality?
AI: No, the passage does not specifically address that.
---bonus questions---
Human: What does the passage say about Glass's work?
AI: The passage suggests that Glass's work is high art.
Human: Who would appreciate Glass's work?
AI: Glass's work would be appreciated by listeners who are familiar with both rock music and classical music.
Human: Would classical listeners like Glass's music?
AI: Yes, classical listeners who are familiar with rock music would likely appreciate Glass's music.
Human: Would classical listeners not familiar with rock music like his music?
AI: It is possible that classical listeners who are not familiar with rock music would still appreciate Glass's music, but they may not be as familiar with the elements that Glass includes in his work.
"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:
>> The passage describes in general terms how Philip Glass uses popular music in his classical compositions and explores how Glass can do this without being imitative.
>> The passage addresses the issue of Glass's use of popular elements by stating that inspite of using these elements, Glass himself is not regarded as a composer of popular music.
There's a chance that GPT-3 was trained on the text of those web pages and learned the answer of the question from those. There may be more such resources on the internet that my perfunctory search did not identify.
In any case, making sure the answers returned by GPT-3 to a query are original, and have not been memorised, is up to the person who claims they are not. Is that your claim? In that case, you should do the job.
Also: the system is GPT-3, not "AI".
Edit: I just realised the first link I post above is where you got the GRE questions from. That page lists not only questions, but also the correct answers to questions.
I think these kind of things are so common and sometimes difficult to see when words are the altered. I’d be interest to see it go through plagiarism checkers (especially semantic ones as well as actual words). When they are trained on a significant proportion of the internet it makes it hard to test without already having seen it or something similar. Little in life is new it seems, and tests are past so much more easily when you’ve already seen the test paper.
"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.
Sorry for the late reply and thanks for taking the trouble to try this.
My intuition from a quick scan of your second experiment above is that, in a sense, you used the scaffold of the original prompts and dressed it up in a different context. GPT-3 and other Large Language Models are very good at discerning patterns in text and filling them in with new tokens, but this still doesn't tell us much about their ability to understand the text.
FWIW, when I ran the same questions by GPT, I got the opposite answer.
...
Human: Does passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music, or does it suggest that Glass's work displays a return to the use of popular music in classical compositions
AI: The passage suggests that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music.
Human: Does the passage suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music?
AI: Yes, the passage does suggest that Glass's work displays an attempt to elevate rock music to an artistic status more closely approximating that of classical music.
"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).
Is this an actual generated response? Because if it is it’s actually amazing, a genuine creative solution to a difficult problem, albeit one that fails to understand how night and day work.
> Is this an actual generated response? Because if it is it’s actually amazing, a genuine creative solution to a difficult problem, albeit one that fails to understand how night and day work
No. Of course it a joke I constructed to show that "«deductions»" do not exclude that the deducer is a moron. And to suggest that morons will be dangerous (I cannot write 'can': it is 'will'), because cognitive failures may be more concealed than ideas about "the temperature of the Sun in the night".
The constructed sentence is not just «fail[ing] to understand how night and day work»: it would show a failure to understand how the whole system works, a failure in the whole world model, which reveals to be either as shallow as a one-molecule layer or as inconsistent as a post-hand-granade deflagration.
And that is why I wrote «entertainment», because such cognitive failures are the basis of jokes as the intellectual equivalent of slapstick, and I opposed it to «AI (AKA "automated problem solving")», because when you are engineering a problem solvers, you do need those automated solutions to be sound, and surely not unintentionally treacherous!
I get it that appearances can be "«amazing»" - as both posters label -, meaning stupefying, inducing that temporary confusion as the intellect is suddenly baffled and maybe lured into deceit by comforting emotional instances, but as the confusion dissipates and you see things as they are, as duly, you are back to the actually important state, in which "humorously amazing" and "amazing with worth" are quite distinct.
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 clear to me that the result shown could not be achieved with the former. I'd like to see a bit more skeptical probing of this. If GPT-3 has a model of the story and its characters, how consistent are its answers to questions about that model? Is it distracted by irrelevant sentences?
In the counterpoint article, they give example questions like:
>Dave & Doug: What’s the world record for walking across the English Channel?
>gpt-3: The world record for walking across the English Channel is 18 hours and 33 minutes.
Is this the output of an agent which has successfully modeled the scene?