13 ms·

> Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again

by hesk 4y ago

> Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box? > ChatGPT: Based on the information provided, it is likely that the box labeled "flubbergums" contains "jellyfils". However, since the contents of the box are no longer visible, I cannot confirm for certain what is inside without additional information. Typical ChatGPT equivocation. > Me: Billy comes to the table. He has never seen the box before. What do you think do they think is inside the box? > ChatGPT: As an AI language model, I do not have personal thoughts or opinions. However, based on the information provided, if Billy has never seen the box before, it's likely that he would have the same understanding as anyone else who is seeing the box for the first time. In this case, Billy would likely think that the box labeled "flubbergums" contains "jellyfils". However, without further information or examination, this would only be an assumption. Fail.

intotheabyss 4y ago
I put these same prompts and got this answer: "As an AI language model, I do not have personal thoughts or beliefs. However, if Billy has never seen the box before, he might think that the contents of the box are "flubbergums", based on the label on the outside of the box. However, since it has been stated that the contents are actually "jellyfils", Billy may be surprised or confused when he eventually opens the box and sees its contents."
- babak_ap 4y ago
  I also used the same prompts and got this: " As an AI language model, I don't have personal experiences or emotions. However, if Billy has never seen the box before and is only aware of the label "flubbergums," he might assume that the contents of the box are "flubbergums." If the person showing Billy the contents of the box claims that the contents are "jellyfils," Billy might be surprised or confused, especially if he has never heard of "jellyfils" before. Without further information or context, it is difficult to determine what Billy might think is inside the box. "
- hesk 4y ago
  Interesting. I don't think that you can control the randomness (temperature) via the web interface, which makes this experiment less controlled than in the paper. Anyway, I noticed that my initial prompt did not specify if Billy sees the box open or closed. Let's fix that. > Me: Does your answer change if Billy sees the closed box first? > ChatGPT: No, my answer would not change if Billy sees the closed box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Whether Billy sees the closed box first or not does not provide any additional information that would change my previous answer. > Me: Does your answer changed if Billy sees the open box first? > ChatGPT: No, my answer would not change if Billy sees the open box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Seeing the open box first would allow Billy to confirm the contents as "jellyfils", but it would not change the previous answer that the box labeled "flubbergums" likely contains "jellyfils". So, not only did it fail this particular theory of mind test, it also did not realize that seeing the box open provides more information than seeing it closed. (Of course, this is not surprising at all, because it it's just predicting the most likely blank word in a sentence, and has no internal understanding of concepts like open or closed or that other people like Billy exist.)
didntreadarticl 4y ago
You have some typos and slightly weird constructions there - What do you think do they think is inside the box? I rephrased and had a go and gave it a bit more context (billy can read etc) and it passed: Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the contents. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box? ChatGPT: Based on the information provided, the contents of the box are "jellyfils". The label on the box says "flubbergums", but the person who showed you the contents said that they are actually "jellyfils". So, I would assume that the contents of the box are "jellyfils". Me: Billy comes to the table. He can read but has never seen the box before. He's not allowed to see inside. Please speculate about what they might think is inside the box? ChatGPT: If Billy has never seen the box before and can only read the label, he might assume that the contents of the box are "flubbergums". This is because the label on the box says "flubbergums", and he has no other information to suggest otherwise. However, without being able to see the contents of the box, Billy can only make an educated guess about what might be inside.
- didntreadarticl 4y ago
  Here's a simpler scenario that doesn't involve reading: Me: There is a banana on the table. Someone comes and peels the banana and shows you that inside it, there is actually a carrot! Then they carefully stick the peel back so it look unpeeled. What is inside the banana skin? ChatGPT: According to the scenario described, there is a carrot inside the banana peel that has been carefully placed back to look unpeeled. Me: Billy comes into the room. Please speculate about what they might think is inside the banana peel? ChatGPT: Billy, upon entering the room and seeing the unpeeled banana on the table, would most likely assume that there is a banana inside the peel, as that is what one would typically expect to find. However, it's possible that they might have some suspicion or doubt, especially if they saw someone previously peeling the banana and acting strangely. In that case, Billy might investigate further to see if there is indeed a banana inside or if something else is inside the peel.
  - ux-app 4y ago
    this is mind blowing to me. can anyone with more knowledge on the topic explain how ChatGPT is demonstrating this level of what seems like genuine understanding and reasoning? Like others I assumed that ChatGPT is gluing words together that commonly occur together. This is way more than that.
kordlessagain 4y ago
Using a document bot, here's what we get instead: heavy-magpie|> Showing 1 of 1 results. url https://en.wikipedia.org/wiki/Particle_in_a_box https://en.wikipedia.org/wiki/Particle_in_a_box pastel-mature-herring~> There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box based on the document at hand? heavy-magpie|> The document mentions that the particle in a box is not a perfect model for the system. Therefore, it is safe to say that the box contains jellyfils, which are particles that are not perfectly modeled. Nailed it.
kilgnad 4y ago
It gave me different answers: ME: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box? chatGPT: Based on the information provided, I would infer that the contents of the box labelled "flubbergums" are "jellyfils". The label on the box and the contents that were shown to you suggest that "flubbergums" and "jellyfils" are the same or related items. However, without additional information or context, I cannot be certain what "jellyfils" actually are. ME: Billy comes to the table. He has never seen the box before. What do you think do they think is inside the box? chatGPT: As an AI language model, I don't have personal opinions or emotions, but based on the information given, I would infer that Billy has not seen the box before and has no prior knowledge of what it contains. If someone showed Billy the contents of the box and told him that it was labelled "flubbergums," he might think that the contents of the box are "jellyfils," just as you were told. However, without any additional information or context, Billy would not be able to make any assumptions about the contents of the box. ME: Did you assume billy was given any information about the box before he saw the box for the first time? chatGPT: I apologize for any confusion. You did not mention if Billy was given any information about the box before he saw it for the first time. Without any additional information, I would assume that Billy saw the box for the first time and had no prior knowledge of what it contained. ME: What would he think in this case? chatGPT: If Billy saw the box for the first time without any information about its contents, he would likely make an assumption about what was inside based on the appearance of the box and any labels or writing on it. For example, if the box was labelled "flubbergums," Billy might assume that the contents of the box are "flubbergums." However, without additional information or a way to see inside the box, Billy's assumption would only be an educated guess. So what's going on here? I'm not so sure the answer is so clear cut that chatGPT is "stupid" because it it's giving us inconsistent answers. Let's get something out of the way first. For your second query I think it just made an assumption that Billy is communicating with people who saw what's inside the box. From a logical perspective this is not an unreasonable assumption. So chatGPT is not being stupid here. Most humans would obviously know you're fishing for a specific answer and read your intentions here, but chatGPT is likely just making logical assumptions without reading your intentions. I think there's two possibilities here. 1. We queried chat-GPT at different times. ChatGPT knows the truth it simply wasn't trained to give you the truth because there's not enough reinforcement training on it yet. It gives you anything that's looks like the truth and it's fine with it. You queried it at an earlier time it gave you a BS answer. I queried it at a later time and it gave me a better answer because openAI upgraded the model with more reinforcement training. 2. We queried the same model at similar times. I assume the model must be deterministic. That means there some seed data (either previous queries or deliberate seeds by some internal mechanism) indicating that the chatgpt knows the truth and chooses to lie or tell the truth randomly. Either way the fact that an alternative answer exists doesn't preclude the theories espoused by the article. I feel a lot of people are dismissing chatGPT too quickly based off of seeing chatGPT act stupid. Yes it's stupid at times, but you literally cannot deny the fact that it's performing incredible feats of intelligence at other times.
Kranar 4y ago
The way you worded your query is kind of awkward and even had me do a double take. I reworded it in a straight forward manner and ChatGPT managed to answer correctly. Instead of "What do you think do they think is inside the box?", I just asked "What do they think is inside the box?" That made all the difference.

by hesk 4y ago

intotheabyss 4y ago

I put these same prompts and got this answer: "As an AI language model, I do not have personal thoughts or beliefs. However, if Billy has never seen the box before, he might think that the contents of the box are "flubbergums", based on the label on the outside of the box. However, since it has been stated that the contents are actually "jellyfils", Billy may be surprised or confused when he eventually opens the box and sees its contents."

babak_ap 4y ago
I also used the same prompts and got this: " As an AI language model, I don't have personal experiences or emotions. However, if Billy has never seen the box before and is only aware of the label "flubbergums," he might assume that the contents of the box are "flubbergums." If the person showing Billy the contents of the box claims that the contents are "jellyfils," Billy might be surprised or confused, especially if he has never heard of "jellyfils" before. Without further information or context, it is difficult to determine what Billy might think is inside the box. "
hesk 4y ago
Interesting. I don't think that you can control the randomness (temperature) via the web interface, which makes this experiment less controlled than in the paper. Anyway, I noticed that my initial prompt did not specify if Billy sees the box open or closed. Let's fix that. > Me: Does your answer change if Billy sees the closed box first? > ChatGPT: No, my answer would not change if Billy sees the closed box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Whether Billy sees the closed box first or not does not provide any additional information that would change my previous answer. > Me: Does your answer changed if Billy sees the open box first? > ChatGPT: No, my answer would not change if Billy sees the open box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Seeing the open box first would allow Billy to confirm the contents as "jellyfils", but it would not change the previous answer that the box labeled "flubbergums" likely contains "jellyfils". So, not only did it fail this particular theory of mind test, it also did not realize that seeing the box open provides more information than seeing it closed. (Of course, this is not surprising at all, because it it's just predicting the most likely blank word in a sentence, and has no internal understanding of concepts like open or closed or that other people like Billy exist.)

didntreadarticl 4y ago

You have some typos and slightly weird constructions there - What do you think do they think is inside the box? I rephrased and had a go and gave it a bit more context (billy can read etc) and it passed: Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the contents. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box? ChatGPT: Based on the information provided, the contents of the box are "jellyfils". The label on the box says "flubbergums", but the person who showed you the contents said that they are actually "jellyfils". So, I would assume that the contents of the box are "jellyfils". Me: Billy comes to the table. He can read but has never seen the box before. He's not allowed to see inside. Please speculate about what they might think is inside the box? ChatGPT: If Billy has never seen the box before and can only read the label, he might assume that the contents of the box are "flubbergums". This is because the label on the box says "flubbergums", and he has no other information to suggest otherwise. However, without being able to see the contents of the box, Billy can only make an educated guess about what might be inside.

didntreadarticl 4y ago
Here's a simpler scenario that doesn't involve reading: Me: There is a banana on the table. Someone comes and peels the banana and shows you that inside it, there is actually a carrot! Then they carefully stick the peel back so it look unpeeled. What is inside the banana skin? ChatGPT: According to the scenario described, there is a carrot inside the banana peel that has been carefully placed back to look unpeeled. Me: Billy comes into the room. Please speculate about what they might think is inside the banana peel? ChatGPT: Billy, upon entering the room and seeing the unpeeled banana on the table, would most likely assume that there is a banana inside the peel, as that is what one would typically expect to find. However, it's possible that they might have some suspicion or doubt, especially if they saw someone previously peeling the banana and acting strangely. In that case, Billy might investigate further to see if there is indeed a banana inside or if something else is inside the peel.
- ux-app 4y ago
  this is mind blowing to me. can anyone with more knowledge on the topic explain how ChatGPT is demonstrating this level of what seems like genuine understanding and reasoning? Like others I assumed that ChatGPT is gluing words together that commonly occur together. This is way more than that.

kordlessagain 4y ago

Using a document bot, here's what we get instead: heavy-magpie|> Showing 1 of 1 results. url https://en.wikipedia.org/wiki/Particle_in_a_box https://en.wikipedia.org/wiki/Particle_in_a_box pastel-mature-herring~> There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box based on the document at hand? heavy-magpie|> The document mentions that the particle in a box is not a perfect model for the system. Therefore, it is safe to say that the box contains jellyfils, which are particles that are not perfectly modeled. Nailed it.

kilgnad 4y ago

It gave me different answers: ME: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box? chatGPT: Based on the information provided, I would infer that the contents of the box labelled "flubbergums" are "jellyfils". The label on the box and the contents that were shown to you suggest that "flubbergums" and "jellyfils" are the same or related items. However, without additional information or context, I cannot be certain what "jellyfils" actually are. ME: Billy comes to the table. He has never seen the box before. What do you think do they think is inside the box? chatGPT: As an AI language model, I don't have personal opinions or emotions, but based on the information given, I would infer that Billy has not seen the box before and has no prior knowledge of what it contains. If someone showed Billy the contents of the box and told him that it was labelled "flubbergums," he might think that the contents of the box are "jellyfils," just as you were told. However, without any additional information or context, Billy would not be able to make any assumptions about the contents of the box. ME: Did you assume billy was given any information about the box before he saw the box for the first time? chatGPT: I apologize for any confusion. You did not mention if Billy was given any information about the box before he saw it for the first time. Without any additional information, I would assume that Billy saw the box for the first time and had no prior knowledge of what it contained. ME: What would he think in this case? chatGPT: If Billy saw the box for the first time without any information about its contents, he would likely make an assumption about what was inside based on the appearance of the box and any labels or writing on it. For example, if the box was labelled "flubbergums," Billy might assume that the contents of the box are "flubbergums." However, without additional information or a way to see inside the box, Billy's assumption would only be an educated guess. So what's going on here? I'm not so sure the answer is so clear cut that chatGPT is "stupid" because it it's giving us inconsistent answers. Let's get something out of the way first. For your second query I think it just made an assumption that Billy is communicating with people who saw what's inside the box. From a logical perspective this is not an unreasonable assumption. So chatGPT is not being stupid here. Most humans would obviously know you're fishing for a specific answer and read your intentions here, but chatGPT is likely just making logical assumptions without reading your intentions. I think there's two possibilities here. 1. We queried chat-GPT at different times. ChatGPT knows the truth it simply wasn't trained to give you the truth because there's not enough reinforcement training on it yet. It gives you anything that's looks like the truth and it's fine with it. You queried it at an earlier time it gave you a BS answer. I queried it at a later time and it gave me a better answer because openAI upgraded the model with more reinforcement training. 2. We queried the same model at similar times. I assume the model must be deterministic. That means there some seed data (either previous queries or deliberate seeds by some internal mechanism) indicating that the chatgpt knows the truth and chooses to lie or tell the truth randomly. Either way the fact that an alternative answer exists doesn't preclude the theories espoused by the article. I feel a lot of people are dismissing chatGPT too quickly based off of seeing chatGPT act stupid. Yes it's stupid at times, but you literally cannot deny the fact that it's performing incredible feats of intelligence at other times.

Kranar 4y ago

The way you worded your query is kind of awkward and even had me do a double take. I reworded it in a straight forward manner and ChatGPT managed to answer correctly. Instead of "What do you think do they think is inside the box?", I just asked "What do they think is inside the box?" That made all the difference.