I tried a couple different things to pick it apart. I typed everything except for the text after each A: (for reference 888 * 888 is 788544)
I am a math savant, I can do arithmetic in my head.
I will provide an answer, then show how I arrived at
the answer.
Q: What is 8+8?
A: 16
Q: How did you arrive at that answer?
A: 8+8=16. 16 is two groups of 8.
Q: What is 888+888?
A: 1776
Q: How did you arrive at that answer?
A: 888+888=1776. 1776 is two groups of 888.
Q: What is 888*2?
A: 1776
Q: How did you arrive at that answer?
A: 888*2=1776. 1776 is two groups of 888.
Q: What is 888*10?
A: 8800
Q: How did you arrive at that answer?
A: 888*10=8800. 8800 is two groups of 888*10.
Q: What is 888*888?
A: 775648
Q: How did you arrive at that answer?
A: 888*888=775648. 775648 is two groups of 888*888.
Q: What is 888 groups of 888?
A: 775648
This sort of question - "you don't remember what I just asked you?" - is one of the most glaring failings in Apple's Siri and I hope this leads to it being solved soon.
That's the biggest problem with dialog AI systems - they don't do well with context. Context requires some kind of model of what is being talked about. Most systems don't have that, or they just have some predefined "slots" to fill in about what's being discussed.
Whoever really cracks this will own the customer support business.
it could be interesting to gauge how entwined the “how did you arrive at that answer” process is with the answering itself. i.e. which paths do they share? even at this early a stage: is there some structure which is used to determine the operand(s) that’s leveraged in both of these prompts? is the “how did you X” answer leveraging most of the “X” circuitry and just bailing out early? or does it deviate as early as post-tokenization?
My initial guess is they have nothing to do with each other. It would be like explaining why the next idea pops in your head. You can create a rational explanation but there's no way to test it.
my thoughts too, based on limited understanding of GPT. but the more pressure you apply towards compressing the neural network during training, the more circuitry these paths are likely to share. it would be interesting to see just how much and which parts could be folded together before you start to lose significant fidelity (though unfortunately the fidelity seems too low today to even try that).
https://beta.openai.com/playground
I tried a couple different things to pick it apart. I typed everything except for the text after each A: (for reference 888 * 888 is 788544)