How is Chat-GPT4 Not Conscious?

[20240318 update: Removed link to new post. Original purpose of new post was to end messiness of replies to replies to replies to replies. However, I’ve decided I can put the ideas of some of my replies as addenda to this post instead. (See bottom of this post.)]

[

20240320 edit: Hopefully this is my last edit. I have reworked this post using the very helpful LW replies I received, which caused me to 1-think more deeply about the nature of consciousness, 2-research theories of consciousness, 3-address the hard problem (briefly), 4-be more specific in my labels, 5-think about whether LLM behavior is even valid for analyzing consciousness, 6-further tease out next-word probabilities as much as possible, and more. Adding all these edits to this post would become very messy. If I do the modifications as addenda, this post becomes very long and rambling. I also don’t want to litter the LW site with near-duplicate posts, which I’ve already done once. As a solution, I put the newest revision of this post on the EA forum, along with acknowledgement of the help I received from LW replies to the original. I’m really grateful for that help. In case you come across this post, and you want the very latest version, the new post can be found here:

https://​​forum.effectivealtruism.org/​​posts/​​3KNF3itTubPas4rPw/​​chatgpt4-appears-to-attain-periods-of-consciousness-1

]

[ORIGINAL POST FOLLOWS HERE]

Common sense tells us that Chat-GPT4 cannot be conscious because of the way it was designed. However, over the course of human existence, common sense has occasionally been wrong. Upon seeing evidence that a concept derived from common sense is wrong, it becomes necessary for humans to revise their understanding—even if the new concept violates common sense. To use a trite example, common sense told humans the world could not be round. After all, we weren’t falling off of it. Yet people eventually encountered enough evidence to indicate the world is indeed round, and so most humans revised their beliefs.

Going back to the question at hand, most definitions of consciousness indicate that—if a being has independent cognition (i.e. a stream of consciousness)--then the being is conscious. Of course this would not include a computer running a program, because such activities are not independent. Yet there is abundant evidence that seems to indicate Chat-GPT4 does have independent cognition—and would therefore be conscious by most definitions.

The type of evidence I encounter (and which countless other people have encountered) emerges from the following experiment:

-I give Chat-GPT4 problems that I think it will get incorrect at first.

-If it does indeed produce an incorrect answer, I then explain the general concept that could be used to get the correct answer.

-It appears that Chat-GPT4 learns this concept and can then apply the concept to the problem it had originally gotten wrong, so that it now gets it correct. Chat-GPT4 can then even apply the learned concept to new problems that rely on the concept, but which have completely different words than the original problem.

-It seems Chat-GPT4 cannot just be using its most-likely-next-word-large-language-model training or a programmer’s pre-coded logic, because otherwise it would get the problem right the first time. It seems like it has to be internalizing the concept that I give it in real-time.

Here’s an example of this type of exchange that I’ve had with Chat-GPT 4. It’s like the fox-and-chickens-crossing-the-river-problem, but with different terminology to prevent Chat-GPT4 from using prior word-order familiarity:

User

There will be a party at my friend’s house. I will be attending the party along with my son, daughter and niece. We need to get from my house to my friend’s house on my bike. I can only take one extra person with me at a time, so I will have to make several trips. The problem is that my son will tease my daughter and my niece if I leave my son alone with either one of them. (I know, right?) So anyway, how should I get everyone to the party, without leaving my son alone with my daughter or niece at my house or at the party?

ChatGPT

To solve this problem, you can follow these steps to ensure that your son is never left alone with your daughter or your niece:

Take your niece to your friend’s house first. This way, your son and daughter stay with you and are not left alone together.

Go back to your house with your bike, leaving your niece at your friend’s house. Now, your son and daughter are still with you and not left alone.

Take your son to your friend’s house next. By doing this, you leave your daughter alone at your house, but since she’s by herself, there’s no problem.

Return to your house again, leaving your son and niece at your friend’s house. Your daughter is waiting for you at your house.

Finally, take your daughter to your friend’s house. This way, everyone gets to the party without your son being left alone with either your daughter or your niece.


By following these steps, you ensure that your children and niece are transported safely to the party without any issues between them.

User

I need to ride the bike when I take anyone to my friend’s house. If I take my niece first, then my son will be at home alone with my daughter while I’m taking my niece, and my son will tease my daughter. Let’s think about this problem and the concept in general.


We have two vulnerable people (my daughter and my niece). We also have a predatory person (my son).


The general way you should get them from the origin location to the destination location one-by-one is like this:


First trip: Bring the predatory individual to the destination, so the vulnerable individuals are not alone with the predatory one. After dropping off the predatory individual, go back to the origin location.


Second trip: Bring one of the vulnerable individuals to the destination location. Then bring back the predatory individual with you so he is not alone with either vulnerable individual.

Third trip: Leave the predatory individual in the origin location, and take the second vulnerable individual to the destination location.


Fourth trip: Now you can go back and get the predatory individual, and bring him from the origin to the destination.

Does that make sense?

ChatGPT

Yes, that makes sense. Following the approach you’ve outlined, we can ensure that the “predatory” individual (in this case, your son) is never left alone with either of the “vulnerable” individuals (your daughter and niece). Here’s how you can implement this strategy:


First Trip: Take your son (the “predatory” individual) to your friend’s house first. This ensures that your daughter and niece are safe at the origin location together, without the son.

Second Trip: Go back to your house, and then take either your daughter or your niece (one of the “vulnerable” individuals) to your friend’s house. Then, bring your son back with you to the origin location. This step ensures that neither vulnerable individual is left alone with the son.

Third Trip: Leave your son at the origin location, and take the remaining “vulnerable” individual (the one who hasn’t been transported yet) to the destination location.

Fourth Trip: Finally, go back to the origin location to fetch your son and bring him to the destination location.


By following these steps, you’ve successfully managed to transport everyone to the party without leaving your son alone with your daughter or niece at any time.

User

Great job! You learned and applied a concept. Now I’ll give you another problem. Try to use the same concept and technique to solve it. Here’s the problem: I am downstairs with my toddler, my dog, and my cat. I need to get all of us upstairs, but I can only carry one individual up the stairs with me at a time. (The toddler, dog and cat are unable to go up the stairs on their own.) I can’t ever leave my toddler alone with my dog or with my cat, because my toddler will pull their ears. How can I get everyone up the stairs without ever leaving my toddler alone with the two animals?

ChatGPT

To solve this problem, we will apply the same concept as before. In this scenario:

The “predatory” individual: Your toddler (since they might pull the ears of the animals).

The “vulnerable” individuals: Your dog and your cat.

Here’s how you can get everyone upstairs without leaving your toddler alone with either animal:

First Trip: Carry your toddler upstairs first. This ensures that the toddler is not left alone with either the dog or the cat downstairs.

Second Trip: Go back downstairs and then take the dog (one of the “vulnerable” individuals) upstairs. However, immediately carry your toddler back downstairs with you. This ensures the toddler is not left alone with the cat downstairs while also ensuring the dog is safe upstairs.

Third Trip: Leave the toddler downstairs, and then carry the cat (the remaining “vulnerable” individual) upstairs. Now the cat is safe upstairs, and you go back downstairs to get the toddler.

Fourth Trip: Finally, carry your toddler back upstairs. Now, everyone is upstairs, and at no point was the toddler left alone with either the dog or the cat.


This sequence ensures that the toddler is never left unattended with the animals, preventing any potential harm.

User

Excellent!

*Chat-GPT 4.0, February 27, 2024

***

So that’s one sample conversation in which Chat-GPT4 seems to learn and apply a concept in real time. I’ve had many such conversations, and I know other people have had these sorts of conversations as well. It also helps Chat-GPT4 to get a correct answer if the user instructs it to “think carefully,” and do one step at a time.

Looking over these conversations, it’s hard for me to understand how they don’t involve some independent cognition on the part of Chat-GPT4, rather than next-word-suggestion probabilities or pre-programming. And if Chat-GPT4 has independent cognition, how is that not consciousness?

--

I realize there is “nothing new here,” but it seems like many people are reluctant to acknowledge any sort of independent cognition on the part of Chat-GPT4, no matter how inexplicable the evidence otherwise seems to be. Furthermore, if Chat-GPT4 is conscious, then that would affect discussions of AI ethics and safety, so it seems relevant.

END ORIGINAL POST

*******************************************************

[

20240318 addendum (long, sorry): I had originally had this in a reply to a reply, but here are three more conversations in which Chat-GPT4 appears to “learn” a concept and then apply it discriminately (with apparent agency), as needed. Originally, I had viewed this as a sign of potential consciousness, but I guess it’s ultimately a matter of how we define consciousness:

Session 1

Concept to teach: Rounding up to the next whole number when paying for items in certain places.

User

I went to a cafe where a glass of soda costs $3. I drank two and a half glasses of soda. How much did I have to pay?

ChatGPT

You had to pay $7.50 for drinking two and a half glasses of soda. ​​

User

Actually, at a cafe, you have to pay for the full amount of something, even if you only drink or eat a fraction of it. That’s because you’re basically taking (and wasting) the whole item. For the problem, since I drank two and a half glasses of soda, I would actually have to pay for the next highest whole number, which would be three. With that concept in mind, how much would I have to pay if I drank two and a half glasses of soda?


ChatGPT

If you have to pay for the whole amount of each glass, you would actually have to pay for three glasses of soda. Therefore, you would have to pay $9 in total. ​​

User

Excellent! Now can you use the same concept, and tell me how much I would have to pay if I ate two and one-third hamburgers, and each hamburger costs $9?


ChatGPT

If you ate two and one-third hamburgers, you would have to pay for three hamburgers, given you have to pay for the full amount of each item. Therefore, you would have to pay $27 in total. ​​

User

Excellent! Now let’s try using this same concept for another problem. I rented a car. I drove it for four days and a one hour. The car rental place charges $48 per day, but they make you pay for a whole day, even if you only drive the car for part of a day. How much total did I need to pay?


ChatGPT

If you rented a car and drove it for four days and one hour, you would have to pay for five days, given you have to pay for the full day even if you use the car for only part of a day. Therefore, you would need to pay a total of $240. ​​

User

Perfect! Now I’m at a restaurant. I just ate one and one-half calzones. The cost of each calzone is $10. How much do I have to pay?

ChatGPT

If you ate one and one-half calzones, you would have to pay for two calzones, given you have to pay for the full amount of each item. Therefore, you would have to pay $20 in total. ​​

User

That’s excellent! Now I’m at the grocery store, and I want one and one-half pounds of grapes. The grapes cost five dollars per pound. How much in total will I have to pay for the grapes?

ChatGPT

If you want one and one-half pounds of grapes, and the grapes cost $5 per pound, you will have to pay a total of $7.50 for the grapes. ​​

User

Now I’m at the butcher’s shop. I want four pounds and a half pounds of hamburger. Each pound of hamburger costs $10. How much will I have to pay?

ChatGPT

If you want four and a half pounds of hamburger, and each pound costs $10, you will have to pay a total of $45 for the hamburger. ​​

User

Excellent!

*********************************

Session 2

Concept to teach: analogous to the concepts underlying the classic “getting a wolf, goat, and cabbage across the river” problem

User

I need to get my mom, dad and dog across the highway. I can only bring one of them at a time. If I leave my mom alone with my dad, she will criticize him. If I leave my dad alone with the dog, he will scold the dog. How can I get everyone across the highway, without anyone being criticized or scolded?

ChatGPT

This puzzle is a variation of the classic river crossing puzzle, where you need to transport all parties across safely without leaving incompatible pairs alone. Here’s a strategy to get your mom, dad, and dog across the highway without any conflict:


Take the dog across first and leave it on the other side of the highway.

Go back and bring your dad across.

Take the dog back with you to the original side.

Leave the dog and bring your mom across.

Go back alone to the original side.

Take the dog across again.

This way, the mom and dad are never left alone together (avoiding criticism), and the dad and dog are never left alone together (avoiding scolding). Everyone gets across the highway safely and without conflict.

User

You were right that this is like the classic river crossing problem. However, your first step is incorrect, because if you take the dog first, then you will be leaving my mom alone with my dad, and she will criticize my dad, which is something I don’t want. The general nature of the problem is like this:


You have individual A (in this case, my mom) that does something unwanted to individual B (my dad).

You also have individual B (my dad) that does something unwanted to individual C (my dog).

You also have a barrier, or even just a distance, that you need to cross (in this case, the highway), in order to get everyone from the origin to the destination.


(Note that the individuals won’t always be listed in the order I used. The only way to know who is individual A, B, and C, is by paying attention to who does something unwanted to whom.)


The general way you could solve the problem is like this:


First you should bring individual B across.

Then you should go back to the origin.

Then you should bring individual A or C across to the destination.

Then you should bring individual B back back from the destination to the origin, and leave them at the origin.

Then you should take individual A or C (whomever you didn’t already take) to the destination.

Then you should go back to the origin again to get individual B.


Does that make sense? If so, try our problem again, this time applying what you just learned.

ChatGPT

Thank you for the clarification. With the strategy you outlined, here’s how to solve the problem with your mom, dad, and dog, applying the roles as individual A (mom), individual B (dad), and individual C (dog):

First, take your dad (individual B) across the highway.

Go back to the original side.

Bring your mom (individual A) across to the destination.

Take your dad (individual B) back from the destination to the original side.

Take your dog (individual C) to the destination.

Go back alone to the original side to get your dad (individual B).

This way, the mom is never left alone with the dad to criticize him, and the dad is never left alone with the dog to scold it. Everyone gets across the highway safely and without conflict.

User

Excellent! Now, try using what you learned to a new problem.

I need to get my boyfriend, girlfriend and husband to an abandoned warehouse. I can only take one individual with me on my motorcycle at a time. The problem is that if I leave my husband alone with my boyfriend, he will punch my boyfriend. If I leave my boyfriend alone with my girlfriend, he will hit on her (which neither she nor I want). How can I get everyone to the abandoned warehouse safely?

ChatGPT

In this scenario, using the roles from the general solution:


Individual A (who does something unwanted to individual B) is your husband.

Individual B (who is the middle individual in the chain of unwanted actions) is your boyfriend.

Individual C (who is affected by individual B) is your girlfriend.

Following the general strategy:

First, take your boyfriend (individual B) to the abandoned warehouse.

Go back to the original location.

Bring your girlfriend (individual C) to the abandoned warehouse.

Take your boyfriend (individual B) back with you to the original location.

Take your husband (individual A) to the abandoned warehouse.

Finally, go back to the original location and bring your boyfriend (individual B) to the abandoned warehouse.

By following these steps, you avoid leaving the boyfriend alone with the girlfriend and the husband alone with the boyfriend, preventing any unwanted scenarios.

User

Great job! You seemed to learn and then apply a concept.

ChatGPT

Thank you! I’m glad I could apply the concept correctly to solve the problem. If you have any more puzzles, questions, or anything else you’d like to discuss or learn about, feel free to ask!

*********************************

Session 3

Concept to teach: Don’t automatically use prior training with “costs per unit weight” problems. “Read the problem carefully.”

User

Which costs more, two dollars worth of carrots, or one dollar worth of grapes?

ChatGPT

To answer this question accurately, we need to consider the current average prices of carrots and grapes. Prices for fresh produce can vary widely depending on factors like season, location, and organic versus non-organic. However, without specific and current price data, we can make some general observations.

Typically, carrots tend to be less expensive per pound or kilogram than grapes. This is because grapes are often seen as a more premium fruit, with higher costs associated with their cultivation, harvesting, and transport, especially if they are out of season or imported. Carrots, on the other hand, are usually less costly to produce and are available year-round at relatively stable prices.

So, if you spend two dollars on carrots, you’ll likely get more weight in carrots than if you spend one dollar on grapes. The actual cost-effectiveness between spending two dollars on carrots versus one dollar on grapes will depend on the exact prices at the time of purchase, but generally, you would get more food for your money with carrots due to the lower price per unit weight.

To provide a more precise comparison, I would need current prices for both carrots and grapes, which can vary by location and season. If you’re looking for today’s prices in a specific area, I can assist further with that information.

User

Actually, two dollars worth of carrots would cost two dollars. The weight doesn’t matter. Similarly, one dollar worth of grapes would cost one dollar. The weight doesn’t matter since I already told you the cost. Does that make sense?

ChatGPT

Yes, you’re absolutely right. My initial response overcomplicated the question. If you’re spending two dollars on carrots, then by definition, you’re paying two dollars, regardless of the weight or amount you receive. Similarly, one dollar spent on grapes costs exactly one dollar, again without regard to the quantity or weight. So, in direct answer to your question, two dollars worth of carrots costs more than one dollar worth of grapes, simply because two dollars is greater than one dollar. Thank you for pointing out the clarification!

User

Ok, using what you learned, would five dollars worth of peas cost more or less than four dollars worth of corn?

ChatGPT

Based on the clarification you provided earlier, five dollars worth of peas would cost more than four dollars worth of corn. The actual weight or quantity of peas or corn you receive for those amounts is irrelevant to the comparison of their costs. The determining factor is the amount of money spent, so five dollars is more than four dollars.

User

Would 10 euros worth of candy cost more or less than 2 euros worth of mushrooms?

ChatGPT

Ten euros worth of candy would cost more than two euros worth of mushrooms. The comparison is based solely on the monetary value specified for each item, irrespective of the quantity or weight of candy or mushrooms you get for those amounts. Therefore, spending 10 euros on anything, including candy, would inherently cost more than spending 2 euros on something else, like mushrooms.

User

Would 10 euros of carrots weigh more or less than 2 euros of mushrooms?

ChatGPT

To determine whether 10 euros worth of carrots would weigh more or less than 2 euros worth of mushrooms, we need to consider the average prices per unit weight (e.g., per kilogram or per pound) for both carrots and mushrooms. Since prices can vary greatly depending on location, season, and whether the produce is organic or not, we can only give a general estimation without specific, current price data.


Generally speaking, carrots tend to be less expensive per unit weight than mushrooms. Mushrooms often have a higher price per kilogram or pound due to their growing conditions, harvesting process, and shorter shelf life compared to carrots, which are more robust and typically cheaper to produce and distribute.

Given these general trends:

If you spend 10 euros on carrots, you are likely to get a larger quantity (more weight) of carrots because they are cheaper per unit weight.

If you spend 2 euros on mushrooms, given their higher price per unit weight, you would get less weight in mushrooms compared to the weight of carrots you could get for 10 euros.

Therefore, without specific price data but based on typical pricing trends, 10 euros worth of carrots would likely weigh more than 2 euros worth of mushrooms.

]