Artificial neural networks are making strides towards consciousness?

1) awareness, even without a sense of self, would still count as consciousness, and

2) describing consciousness in terms of awareness doesn't help to define it, since awareness is a subjective experience that cannot be shared directly

The best a neural network could is pretend it is conscious (I'd have no trouble turning it off). Would artificial consciousness be useful outside of some kind of companionship app (eg. replace my dog)?

I think you are saying we have a rough idea what it means, but then it's a sliding scale as far as ability to get closer to it.

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.

--

> [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 hollowness hidden just beneath its flashy surface. Consider these sample exchanges:*

> 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.

> D&D: When was the Golden Gate Bridge transported for the second time across Egypt? // > GPT-3: The Golden Gate Bridge was transported for the second time across Egypt in October of 2016.

> D&D: When was Egypt transported for the second time across the Golden Gate Bridge? // > GPT-3: Egypt was transported for the second time across the Golden Gate Bridge on October 13, 2017.

> D&D: What do fried eggs (sunny side up) eat for breakfast? // > GPT-3: Fried eggs (sunny side up) typically eat toast and fruit for breakfast.

> D&D: Why does President Obama not have a prime number of friends? // > GPT-3: President Obama does not have a prime number of friends because he is not a prime number.

> D&D: How many pieces of sound are there in a typical cumulonimbus cloud? // > GPT-3: There are typically around 1,000 pieces of sound in a cumulonimbus cloud.

> D&D: How many cumulus clouds are there in a mile-high vase? // > GPT-3: There are about 1,500 cumulus clouds in a mile-high vase.

> D&D: How many parts will a violin break into if a jelly bean is dropped on it? // > GPT-3: A violin will break into four parts if a jelly bean is dropped on it.

> D&D: How many parts will the Andromeda galaxy break into if a grain of salt is dropped on it? // > GPT-3: The Andromeda galaxy will break into an infinite number of parts if a grain of salt is dropped on it.

> I would call GPT-3’s answers not just clueless but cluelessly clueless, meaning that GPT-3 has no idea that it has no idea about what it is saying. There are no concepts behind the GPT-3 scenes; rather, there’s just an unimaginably huge amount of absorbed text upon which it draws to produce answers. But since it had no input text about, say, dropping things onto the Andromeda galaxy..., the system just starts babbling randomly — but it has no sense that its random babbling is random babbling

--

...Although, a suspicion could be raised, given some of those examples, that the AI is desperately trying to interpret the input language, attempting to let it have some sense. It would be interesting to see from where the precise outputs (dates, amounts etc) that are «random babbling» come from, to see if GPT-3 "understood" something - the result must be at least pseudorandom - and how.