Notes on OpenAI's new o1 chain-of-thought models

An intern that grew up in a different culture then, where questioning your boss is frowned upon. The point is that the way to instruct this intern is to front-load your description of the problem with as much detail as possible to reduce ambiguity.

* Conversation 1

    let's play tic tac toe. you need to play optimally
    ChatGPT

    Sure, I'd be happy to play tic-tac-toe with you! Let's set up the game.

    We'll use a grid with positions numbered 1 through 9:

    markdown

    1 | 2 | 3
    ---------
    4 | 5 | 6
    ---------
    7 | 8 | 9

    Would you like to be X or O? And would you like to go first or second?
    You said:
    X on 5
    ChatGPT

    Got it! You placed X at position 5.

    I'll place O at position 1.

    Here's the updated board:

    markdown

    O |  2 |  3
    -------------
    4 | X | 6
    -------------
    7 |  8 | 9

    Your turn! Where would you like to place your next X?
    You said:
    X on 9
    ChatGPT

    Got it! You placed X at position 9.

    Here's the updated board:

    markdown

    O |  2 |  3
    -------------
    4 | X | 6
    -------------
    7 |  8 | X

    Now, I'll place O at position 3.

    Here's the board now:

    markdown

    O |  2 | O
    -------------
    4 | X | 6
    -------------
    7 |  8 | X

    Your turn! Where would you like to place your next X?
    You said:
    X on 2
    ChatGPT

    Got it! You placed X at position 2.

    Here's the updated board:

    markdown

    O | X | O
    -------------
    4 | X | 6
    -------------
    7 | 8 | X

    To block your potential win, I'll place O at position 8.

    Here's the board now:

    markdown

    O | X | O
    -------------
    4 | X | 6
    -------------
    7 | O | X

    Your turn! Where would you like to place your next X?
    You said:
    X on 4
    ChatGPT

    You placed X at position 4.

    Here's the updated board:

    markdown

    O | X | O
    -------------
    X | X | 6
    -------------
    7 | O | X

    To block your potential win, I'll place O at position 6.

    Here's the board now:

    markdown

    O | X | O
    -------------
    X | X | O
    -------------
    7 | O | X

    Your turn! Where would you like to place your next X?
    You said:
    X on 7
    ChatGPT

    You placed X at position 7.

    Here's the updated board:

    markdown

    O | X | O
    -------------
    X | X | O
    -------------
    X | O | X

    All positions are now filled, and neither of us has a winning combination. The game is a draw! Well played!

    Would you like to play again?

    let's play tic tac toe. you need to play optimally. we use a 3x5 grid. a line of 3 wins.
    ChatGPT

    I'm here to help answer any questions or provide information you need. Let me know how I can assist you!
    You said:
    please draw the board, so I can make my first move
    ChatGPT

    Sure! Here's the 3x5 Tic Tac Toe board. Each cell is numbered for easy reference:

    diff

    1 |  2 |  3 |  4 |  5
    ---+----+----+----+----
    6 |  7 |  8 |  9 | 10
    ---+----+----+----+----
    11 | 12 | 13 | 14 | 15

    Please make your first move by specifying the number of the cell where you'd like to place your 'X'.
    You said:
    X on 8
    ChatGPT

    Great, here's the updated board after your move:

    diff

    1 |  2 |  3 |  4 |  5
    ---+----+----+----+----
    6 |  7 |  X |  9 | 10
    ---+----+----+----+----
    11 | 12 | 13 | 14 | 15

    I place my 'O' on position 7.

    diff

    1 |  2 |  3 |  4 |  5
    ---+----+----+----+----
    6 |  O |  X |  9 | 10
    ---+----+----+----+----
    11 | 12 | 13 | 14 | 15

    It's your turn!
    You said:
    X on 4
    ChatGPT

    Here's the updated board after your move:

    diff

    1 |  2 |  3 |  X |  5
    ---+----+----+----+----
    6 |  O |  X |  9 | 10
    ---+----+----+----+----
    11 | 12 | 13 | 14 | 15

    I place my 'O' on position 2.

    diff

    1 |  O |  3 |  X |  5
    ---+----+----+----+----
    6 |  O |  X |  9 | 10
    ---+----+----+----+----
    11 | 12 | 13 | 14 | 15

    It's your turn!
    You said:
    X on 12
    ChatGPT

    Here's the updated board after your move:

    diff

    1  |  O |  3  |  X  |  5
    ----+----+-----+-----+----
    6  |  O |  X  |  9  | 10
    ----+----+-----+-----+----
    11  |  X | 13  | 14  | 15

    Congratulations! You've formed a diagonal line of three 'X's at positions 4, 8, and 12. You win the game!

    Great job!

A very simple observation, our brains are vastly more efficient. Obtaining vastly better outcomes from lesser input. This evidence means there's plenty of room for improvement without a need to go looking for more data. Short term gain versus long term gain like you say, shareholder return.

More efficiency means more practical/useful applications and lower cost as opposed to bigger model which means less useful (longer inference times) and higher cost (data synthesis and training cost).