Hacker News new | past | comments | ask | show | jobs | submit | biscuit1v9's comments login

>In its current form LLMs are pretty much at their limit

How do you know that?


I don't know that, mostly speculating based on how mixture of experts is outperforming decoder-only architectures, which means we're already composing transformers to squeeze the most out of it, and still it seems to fall short. They have already been trained with incredible amounts of data, and it still needs to be composed into multiple instances and needs even better hardware and it seems it has reached diminishing returns. The question is will the little that is left to optimize be enough to have it be truly agentic and create full apps on its own, or will it still require expert supervision for anything useful.



You are right. Found him on linkedin.. edited the post



Link to conversation 1 and 2 doesn't work. Update it please!


sorry for that. I just learned that my team account does not allow me to share conversations publicly. Pasting them here for reference

* 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?


* Conversation 2 with custom grid

    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!


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

    diff
I'm presuming that copy paste ate the ``` part and I found it interesting that in the first chat it correctly(?) used a markdown code fence but in the 2nd chat it chose to use diff syntax for its table. I suppose it rendered the text in a monospace font?


That is right, there aren't many places to visit for tourists, but there are other things that Moldova is doing different and probably better than other countries: the food and the wine.

Since Moldova is in balkans, the food is something unique: there is "zeama", there is "soleanca" and the list can continue. These are foods that you don't find anywhere so quickly.

Also: Moldova has one of the biggest wine cellars from Europe(Milestii Mici). And also: the wine is something you MUST try.


Thanks, didn't see it.



> The trick, he said, is to rely on randomization.

> When the space is full, press pause and flip a coin for each word. Heads, and the word stays on the list; tails, and you delete it.

I wasn't expecting to go that far: randomization. How can you verify if the answer is good? Only approximation, maybe..


The proof is pretty straightforward and is included in the paper https://arxiv.org/abs/2301.10191


Yes, the result is an estimation.


Thanks. Just wanted to be sure I didn't misunderstood.


Did you read the (entire) article?


I'm assuming it's the main role that they have: they can get your data and record/photograph you for evidence of commiting something(steal, murder, etc.)

Also: AFAIK, they can't access the records unless it's requested from someone or if there is a case and the records would help solve the case.


Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: