For your “better example”, it can literally already do this. I just tested this with 4o and it worked great (and I’ll say more accurately than a human would estimate most likely). I used 4o because it appears that the chain of thought models don’t accept image input yet.
I don’t want to post identifiable information so I will avoid linking to the convo or posting screenshots but you can try it yourself. I took 5 pictures of a child’s magnetic tile sitting on the floor and here is the output:
Me: (5 pictures attached)
Me: Estimate how much this weighs.
ChatGPT 4o:
From the images, it appears that this is a small, plastic, transparent, square object, possibly a piece from a magnetic tile building set (often used in educational toys). Based on the size and material, I estimate this piece to weigh approximately 10 to 20 grams (0.35 to 0.7 ounces). If it's part of a toy set like Magna-Tiles, the weight would be on the lower end of that range.
But for some reason I have a feeling this isn’t going to be good enough for you and the goalposts are about to be pushed back even farther.
“In the cypher example, all it’s doing is basically using a separate model to break a particular model into chain of thought, and prompting that. And there is plenty in the training set of GPT about decrypting cyphers.”
I’m sorry, but are you suggesting that applying a previously learned thought process to new variables isn’t reasoning? Does your definition of reasoning now mean that it’s only reasoning if you are designing a new-to-you chain of thought? As in, for deciphering coded messages, you’re saying that it’s only “reasoning” if it’s creating net new decoding methodologies? That’s such an absurd goalpost.
You wouldn’t have the same goalposts for humans. All of your examples I bet the average human would fail at btw. Though that may just be because the average human is bad at reasoning haha.
I didn't ask for an estimation, I asked for the exact weight. A human can do this given the process I described.
If the chain of thought was accurate, then it would be able to give you an internemdiate output of the shape in some 3d format spec. But nowhere in the model does that data exist, because its not doing any reasoning, it just still all statistically best answers.
I mean sure, you could train a model on how to create 3d shapes out of pictures, but again, thats not reasoning.
I don't get why people are so attached to these things being intelligent. We all agree that they are usefull. Like it shouldn't matter if its not intelligent to you or anyone else.
I don’t want to post identifiable information so I will avoid linking to the convo or posting screenshots but you can try it yourself. I took 5 pictures of a child’s magnetic tile sitting on the floor and here is the output:
Me: (5 pictures attached)
Me: Estimate how much this weighs.
ChatGPT 4o: From the images, it appears that this is a small, plastic, transparent, square object, possibly a piece from a magnetic tile building set (often used in educational toys). Based on the size and material, I estimate this piece to weigh approximately 10 to 20 grams (0.35 to 0.7 ounces). If it's part of a toy set like Magna-Tiles, the weight would be on the lower end of that range.
But for some reason I have a feeling this isn’t going to be good enough for you and the goalposts are about to be pushed back even farther.
“In the cypher example, all it’s doing is basically using a separate model to break a particular model into chain of thought, and prompting that. And there is plenty in the training set of GPT about decrypting cyphers.” I’m sorry, but are you suggesting that applying a previously learned thought process to new variables isn’t reasoning? Does your definition of reasoning now mean that it’s only reasoning if you are designing a new-to-you chain of thought? As in, for deciphering coded messages, you’re saying that it’s only “reasoning” if it’s creating net new decoding methodologies? That’s such an absurd goalpost.
You wouldn’t have the same goalposts for humans. All of your examples I bet the average human would fail at btw. Though that may just be because the average human is bad at reasoning haha.