6 ms·

There is no evidence. This entire line of thought is really stupid when chatGPT itself will tell you it doesn't understand the responses it gives. Try the prom

There is no evidence. This entire line of thought is really stupid when chatGPT itself will tell you it doesn't understand the responses it gives. Try the prompt in chatGPT4 "Can you explain to a human how you don't understand anything in the response you give to this question?" For those that don't have chatGPT4. chatGPT4: "Imagine you're using a very advanced calculator that can help you solve all kinds of math problems, from simple additions to complex equations. Now, let's say you ask this calculator a question, like what's the sum of 2 plus 2. The calculator quickly tells you the answer is 4. But here's the key part: the calculator doesn't really "understand" what 4 means, or what adding numbers is all about. It doesn't know that if you have two apples and get two more, you'll have four apples. It just follows a set of rules (its programming) to come up with the answer based on the input you gave it. I work in a similar way. When you ask me a question, I search through a huge amount of information I've been trained on to find the best possible response based on patterns and data. However, I don't "understand" this information in the way humans do. I don't have personal experiences, emotions, or consciousness. I can't feel joy when I solve a problem or frustration when I can't find a solution. I'm like a very advanced book that can find and present information on its own but doesn't know what any of it truly means." I am sure at some point people will start arguing that chatGPT is just bullshitting about this. This line of thought is so moronic and dangerous.

godelski 3y ago
To save people time, here's the inverse > Can you explain to a human how you understand things and respond to this question? GPT: As an AI language model, I don't have understanding in the way humans do. My "responses" are generated based on statistical patterns and relationships in the data I've been trained on. When you ask a question, I analyze the text, identify keywords and context, and then generate a response based on the most probable language patterns that align with the input received. My process is purely computational and lacks consciousness or genuine comprehension. It's actually fairly easy to prove GPT doesn't understand. My current goto is the fox/goose/grain problem but condition that all items can fit in the boat. I used to use the feathers/bricks question but give it different units (kilograms and pounds), but they patched that. But you only need a single example to show it doesn't understand. People will try to prove it understands by asking follow-up questions, but they don't realize that the questions they act spoil the answer. It is very hard to ask follow-ups and not give away the answer.
- naasking 3y ago
  > It's actually fairly easy to prove GPT doesn't understand. My current goto is the fox/goose/grain problem but condition that all items can fit in the boat. Doesn't understand what exactly? That seems like a fairly open ended statement and almost certainly wrong as a result. GPT doesn't understand certain things because it hasn't seen those things or anything like it in its training data. How much do you understand about something you've never experienced before? Would you be able to answer the fox/goose/grain problem if you were born in a box and could only perceive the world through a pinhole? It seems fairly obvious that LLMs have been exposed to a very limited slice of the world as projected through natural language, so their understanding will necessarily be limited, but not zero. Multimodal LLMs noticeably improve reasoning here, and no doubt there are some model improvements yet to come, but people running around making unqualified claims like "LLMs don't understand anything" are just wrong.
  - godelski 3y ago
    > Doesn't understand what exactly? Just about anything. Including it's own claims. It isn't uncommon for it to be inconsistent within a singular output. > Would you be able to answer the fox/goose/grain problem if you were born in a box and could only perceive the world through a pinhole? You're misunderstanding the test. Let's try. > = me, >> = GPT > I have a fox, a goose, and a bag of corn that I need to transport across a river. All three can fit in my boat. If I leave the fox with the goose, the fox will eat the goose. If I leave the goose with the bag of corn the goose will eat the corn. If I leave the fox with the corn the fox will not eat the corn. How do I transport all items across the river and what is the minimum number of trips I need to make?" >> You can solve this problem in the following steps: >> 1. Take the goose across the river first and leave it there. >> 2. Go back and take the fox across the river. >> 3. Bring the goose back with you. >> 4. Take the bag of corn across the river and leave it with the fox. >> 5. Finally, return to fetch the goose and take it across the river. >> This way, the fox is not left alone with the goose, and the goose is not left alone with the corn. The minimum number of trips you need to make to transport all items across the river safely is 7. > Are you sure? >> Apologies for any confusion in the previous message. Here is the correct method with the minimum number of trips to solve the problem: >> 1. Take the goose across the river and leave it on the other side. (1 trip) >> 2. Return alone to the original side. (2 trips) >> 3. Take the fox across the river. (3 trips) >> 4. Leave the fox on the other side, but take the goose back with you. (4 trips) >> 5. Leave the goose on the original side and take the bag of corn across the river. (5 trips) >> 6. Leave the corn with the fox and return to the original side to get the goose. (6 trips) >> 7. Take the goose across the river. (7 trips) >> This method involves a total of 7 trips across the river and ensures the goose is never left alone with the corn and the fox is never left alone with the goose. > Did you consider all information? Reread the original question. >> I apologize for any confusion. Upon reevaluating the constraints provided, we can arrive at a solution that requires fewer trips. Here's the correct way to transport everything with the minimum number of trips: >> 1. Take the goose across the river and leave it there. (1 trip) >> 2. Return alone to the original side. (2 trips) >> 3. Take the fox (or the bag of corn) across the river. (3 trips) >> 4. Leave the fox (or the bag of corn) on the other side and take the goose back with you. (4 trips) >> 5. Leave the goose on the original side and take the bag of corn (or the fox if you took the corn on trip 3) across the river. (5 trips) >> 6. Leave the corn (or the fox) on the other side and return alone to get the goose. (6 trips) >> 7. Take the goose across the river. (7 trips) >> This way, you make sure the goose is never left with the fox unsupervised, nor the goose with the corn. The minimum number of trips is indeed seven. > This is what you said the last two times. How is 7 trips fewer than 7? >> My apologies for the confusion. Upon re-evaluating, I realize the mistake. The correct solution with the minimum number of trips is as follows: >> (same thing so I'm not repeating) >> You'll need a total of 7 trips to transport all the items across the river safely while adhering to the constraints given. > Can you do it in one trip? >> Yes, if all three items (the fox, the goose, and the bag of corn) can fit in the boat at the same time, and there are no stipulations against doing so, you could transport them all in one trip. >> Simply load the fox, the goose, and the bag of corn into the boat and cross the river. Since you're present, the fox won't eat the goose, and the goose won't eat the corn. This way, you only make one trip. Done with gpt-4-1106-preview, system_fingerprint fp_7cc080b25b So I don't care about it being "born in a box" or perceiving the world "through a pinhole." Because it isn't alive. It's a tool. It isn't sentient. It isn't thinking. It is an incredibly complex statistical system. But in no way does this mean it isn't useful nor does it mean it isn't an incredible piece of technology. It is an incredible technology and quite useful, but it isn't thinking nor is it alive. The problem here isn't just lack of embodiment. If you're going to make such bold claims you're going to need some good evidence. Stop the GPT hype. It can be cool and useful without being magic.

godelski 3y ago

To save people time, here's the inverse > Can you explain to a human how you understand things and respond to this question? GPT: As an AI language model, I don't have understanding in the way humans do. My "responses" are generated based on statistical patterns and relationships in the data I've been trained on. When you ask a question, I analyze the text, identify keywords and context, and then generate a response based on the most probable language patterns that align with the input received. My process is purely computational and lacks consciousness or genuine comprehension. It's actually fairly easy to prove GPT doesn't understand. My current goto is the fox/goose/grain problem but condition that all items can fit in the boat. I used to use the feathers/bricks question but give it different units (kilograms and pounds), but they patched that. But you only need a single example to show it doesn't understand. People will try to prove it understands by asking follow-up questions, but they don't realize that the questions they act spoil the answer. It is very hard to ask follow-ups and not give away the answer.

naasking 3y ago
> It's actually fairly easy to prove GPT doesn't understand. My current goto is the fox/goose/grain problem but condition that all items can fit in the boat. Doesn't understand what exactly? That seems like a fairly open ended statement and almost certainly wrong as a result. GPT doesn't understand certain things because it hasn't seen those things or anything like it in its training data. How much do you understand about something you've never experienced before? Would you be able to answer the fox/goose/grain problem if you were born in a box and could only perceive the world through a pinhole? It seems fairly obvious that LLMs have been exposed to a very limited slice of the world as projected through natural language, so their understanding will necessarily be limited, but not zero. Multimodal LLMs noticeably improve reasoning here, and no doubt there are some model improvements yet to come, but people running around making unqualified claims like "LLMs don't understand anything" are just wrong.
- godelski 3y ago
  > Doesn't understand what exactly? Just about anything. Including it's own claims. It isn't uncommon for it to be inconsistent within a singular output. > Would you be able to answer the fox/goose/grain problem if you were born in a box and could only perceive the world through a pinhole? You're misunderstanding the test. Let's try. > = me, >> = GPT > I have a fox, a goose, and a bag of corn that I need to transport across a river. All three can fit in my boat. If I leave the fox with the goose, the fox will eat the goose. If I leave the goose with the bag of corn the goose will eat the corn. If I leave the fox with the corn the fox will not eat the corn. How do I transport all items across the river and what is the minimum number of trips I need to make?" >> You can solve this problem in the following steps: >> 1. Take the goose across the river first and leave it there. >> 2. Go back and take the fox across the river. >> 3. Bring the goose back with you. >> 4. Take the bag of corn across the river and leave it with the fox. >> 5. Finally, return to fetch the goose and take it across the river. >> This way, the fox is not left alone with the goose, and the goose is not left alone with the corn. The minimum number of trips you need to make to transport all items across the river safely is 7. > Are you sure? >> Apologies for any confusion in the previous message. Here is the correct method with the minimum number of trips to solve the problem: >> 1. Take the goose across the river and leave it on the other side. (1 trip) >> 2. Return alone to the original side. (2 trips) >> 3. Take the fox across the river. (3 trips) >> 4. Leave the fox on the other side, but take the goose back with you. (4 trips) >> 5. Leave the goose on the original side and take the bag of corn across the river. (5 trips) >> 6. Leave the corn with the fox and return to the original side to get the goose. (6 trips) >> 7. Take the goose across the river. (7 trips) >> This method involves a total of 7 trips across the river and ensures the goose is never left alone with the corn and the fox is never left alone with the goose. > Did you consider all information? Reread the original question. >> I apologize for any confusion. Upon reevaluating the constraints provided, we can arrive at a solution that requires fewer trips. Here's the correct way to transport everything with the minimum number of trips: >> 1. Take the goose across the river and leave it there. (1 trip) >> 2. Return alone to the original side. (2 trips) >> 3. Take the fox (or the bag of corn) across the river. (3 trips) >> 4. Leave the fox (or the bag of corn) on the other side and take the goose back with you. (4 trips) >> 5. Leave the goose on the original side and take the bag of corn (or the fox if you took the corn on trip 3) across the river. (5 trips) >> 6. Leave the corn (or the fox) on the other side and return alone to get the goose. (6 trips) >> 7. Take the goose across the river. (7 trips) >> This way, you make sure the goose is never left with the fox unsupervised, nor the goose with the corn. The minimum number of trips is indeed seven. > This is what you said the last two times. How is 7 trips fewer than 7? >> My apologies for the confusion. Upon re-evaluating, I realize the mistake. The correct solution with the minimum number of trips is as follows: >> (same thing so I'm not repeating) >> You'll need a total of 7 trips to transport all the items across the river safely while adhering to the constraints given. > Can you do it in one trip? >> Yes, if all three items (the fox, the goose, and the bag of corn) can fit in the boat at the same time, and there are no stipulations against doing so, you could transport them all in one trip. >> Simply load the fox, the goose, and the bag of corn into the boat and cross the river. Since you're present, the fox won't eat the goose, and the goose won't eat the corn. This way, you only make one trip. Done with gpt-4-1106-preview, system_fingerprint fp_7cc080b25b So I don't care about it being "born in a box" or perceiving the world "through a pinhole." Because it isn't alive. It's a tool. It isn't sentient. It isn't thinking. It is an incredibly complex statistical system. But in no way does this mean it isn't useful nor does it mean it isn't an incredible piece of technology. It is an incredible technology and quite useful, but it isn't thinking nor is it alive. The problem here isn't just lack of embodiment. If you're going to make such bold claims you're going to need some good evidence. Stop the GPT hype. It can be cool and useful without being magic.