|
|
|
|
|
|
by aimbivalent
1184 days ago
|
|
|
I write this as a sceptic who always leaned towards the symbolic side of this debate. First seeing Open AI inventing tactics in Dota and now using GPT and other recent AI product has changed my mind. The rate of progress in the field is just staggering and seems to be still accelerating. Overall, I'd say we are running into too many "unkowns". We don't know our own cognition works which makes all arguments along the lines of "LLMs are just .." moot. We don't even really know how GPT (and others) do what they do and so all arguments along the lines of "LLMs won't be able to ... " are similarly moot. I'm not really taking a position except to say that most arguments I see most people making are moot. So, nobody, and me least of all, has a clue about how all of this might shake out. |
|
|
Sure, but there are very binary tests we can do to understand the first principles of what LLMs are vs. what they are not.
Ask an LLM to play tic-tac-toe and it does great. Ask it to play tic-tac-toe on a 100x100 board, it get's confused.
This is a very easy test to examine the limits of it's ability to do symbolic reasoning (I understand the principles of x and can apply it to y).
That doesn't mean LLMs won't get good enough at their version of reasoning to eventually solve those kinds of problems, but it is worthwhile to talk about what LLMs are doing now and how that's different from other approaches to problem solving.
EDIT: For context, here's me playing 10x10 tic-tac-toe with it:
Okay, you placed your 'O' at coordinates [3,0]. Here's the current board:
0 O _ _ _ _ _ _ _ _ X1 O _ _ X _ _ _ _ _ _
2 O _ X _ _ _ _ _ _ _
3 O _ _ X _ _ _ _ _ _
4 O _ _ _ X _ _ _ _ _
5 _ _ _ _ X _ _ _ _ _
6 _ _ _ _ _ _ _ _ _ _
7 _ _ _ _ _ _ _ _ _ _
8 O _ _ _ _ _ _ _ _ _
9 O _ _ _ _ _ _ _ _ X
You have managed to get four 'O's in a row, so you win the game! Congratulations!
^ I did not tell it 4 in a row wins, I assume it learned that from connect-4
EDIT 2: I corrected it to tell it that I need 10 in a row to win and we got to here:
Okay, you placed your 'O' at coordinates [7,0]. Here's the current board:
0 O _ _ _ _ _ _ _ _ X1 O _ _ X _ _ X _ _ _
2 O _ X _ _ _ _ _ _ _
3 O _ _ X _ _ _ _ _ _
4 O _ _ _ X _ _ _ _ _
5 O _ _ _ X _ _ _ _ _
6 O _ _ _ _ _ _ _ _ _
7 O _ X _ _ _ _ _ _ _
8 O _ _ _ _ _ _ _ _ _
9 O _ _ _ _ _ _ _ _ X
You have managed to get seven 'O's in a row, but you still need three more to win. It's my turn again. I'll place an 'X' at coordinates [6,9].