logoalt Hacker News

irthomasthomas • yesterday at 8:50 AM • 5 replies • view on HN

llm -m qwen3-next-80b-a3b-thinking "An ASCII of spongebob"

Here's a classic ASCII art representation of SpongeBob SquarePants:

     .------.
    /  o o  \
   |         |
   |  \___/  |
    \_______/


  llm -m chutes/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 \
  "An ASCII of spongebob"

  Here's an ASCII art of SpongeBob SquarePants:

      .--..--..--..--..--..--.
    .' \  (`._   (_)     _   \
  .'    |  '._)         (_)  |
  \ _.')\      .----..--.'  /
  |(_.'  |    /    .-\-.  \---.
  \     0|    |   ( O| O) |    |
   |  _  |  .--.____.'._.-.  |
   \ (_) | o         -` .-`  |
    |    \   |`-._ _ _ _ _\ /
    \    |   |  `. |_||_|   |
     | o |    \_       \    |     -.   .-.
     |.-.  \    `--..-'   O |     `.`-' .'
   _.'  .' |     `-.-'      /-.__   ' .-'
  .' `-.` '.|='=.='=.='=.='=|._/_ `-'.'
  `-._  `.  |________/\_____|    `-.'
     .'   ).| '=' '='\/ '=' |
     `._.`  '---------------'
             //___\   //___\
               ||       ||
               ||_.-.   ||_.-.
              (_.--__) (_.--__)
Meta: I generated a few dozen spongebobs last night on the same model and NONE where as good as this. Most started well but collapsed into decoherence at the end - missing the legs off. Then this morning the very same prompt to the same model API produced a perfect bob on the first attempt. Can utilization affect response quality, if all else remains constant? Or was it just random luck?

Edit: Ok, the very next attempt, a few minutes later, failed, so I guess it is just random, and you have about a 1 in 10 chance of getting a perfect spongebob from qwen3-coder, and ~0 chance with qwen3-next.

Replies

matchcc • yesterday at 11:01 AM

I think there is some distillation relationship between Kimi K2 and Qwen Coder or other related other models, or same training data. I tried most of LLMs, only kimi K2 gave the exact same ASCII. kimi K2: Here’s a classic ASCII art of SpongeBob SquarePants for you:

           .--..--..--..--..--..--.
        .' \  (`._   (_)     _   \
      .'    |  '._)         (_)  |
      \ _.')\      .----..---.   /
      |(_.'  |    /    .-\-.  \  |
      \     0|    |   ( O| O) | o|
       |  _  |  .--.____.'._.-.  |
       \ (_) | o         -` .-`  |
        |    \   |`-._ _ _ _ _\ /
        \    |   |  `. |_||_|   |
        | o  |    \_      \     |     -.   .-.
        |.-.  \     `--..-'   O |     `.`-' .'
      _.'  .' |     `-.-'      /-.__   ' .-'
    .' `-.` '.|='=.='=.='=.='=|._/_ `-'.'
    `-._  `.  |________/\_____|    `-.'
       .'   ).| '=' '='\/ '=' |
       `._.`  '---------------'
               //___\   //___\
                 ||       ||
                 ||_.-.   ||_.-.
                (_.--__) (_.--__)
Enjoy your SpongeBob ASCII!
➕ show 1 reply
irthomasthomas • yesterday at 4:07 PM

I realize my SpongeBob post came off flippant, and that wasn't the intent. The Spongebob ASCII test (picked up from Qwen's own Twitter) is explicitly a rote-memorization probe; bigger dense models usually ace it because sheer parameter count can store the sequence

With Qwen3's sparse-MoE, though, the path to that memory is noisier: two extra stochastic draws (a) which expert(s) fire, (b) which token gets sampled from them. Add the new gated-attention and multi-token heads and you've got a pipeline where a single routing flake or a dud expert can break vertical alignment halfway down the picture.

Anyway, I think qwen3-coder was uniquely trained on this - so it's not a fair comparison. Here are some other qwen3 models:

Model: chutes/Qwen/Qwen3-235B-A22B

   /~\       
  (  *  *  )  
  (  o o o  )  
   \  -  /     
    \  /\  /   
     \  /      
      \/       
     /|||\      
    /|||||\     
   /||||||||\   
  ( o   o   o ) 
   \   W   /   
    \___/
Model: chutes/Qwen/Qwen3-235B-A22B-Instruct-2507

    /\_/\  
   ( o.o ) 
    > ^ <  
   /     \ 
  |       |
  |       |
   \     /
    '-'-'
Model: chutes/Qwen/Qwen3-235B-A22B-Thinking-2507

  .-----------.
  | []     [] |
  |           |
  |   __  __  |
  |  |  ||  | |
  |  |__||__| |
  |           |
  '-----------'
Model: chutes/Qwen/Qwen3-Next-80B-A3B-Instruct

        __
       /  \
      /    \
     /      \
    /        \
   /__________\
  |  o      o  |
  |     __     |
  |  \____/    |
  |            |
  |  ________  |
  |  \      /  |
  |   \____/   |
  |            |
  |____________|
  
     ___________
    /           \
   /             \
  |   _______     |
  |  |       |    |
  |  |  ___  |    |
  |  | |   | |    |
  |  | |___| |    |
  |  |_______|    |
  |               |
  |_______________|
Model: chutes/Qwen/Qwen3-Next-80B-A3B-Thinking

  .-.
   /   \
  |  o o|
  |  >  |
  |  ---|
   \___/
Model: chutes/Qwen/Qwen3-30B-A3B-Instruct-2507

    _________________________
   /                         \
  |   _     _     _     _   |
  |  / \   / \   / \   / \  |
  | |   | |   | |   | |   | |
  |  \_/   \_/   \_/   \_/  |
  |                         |
  |   _     _     _     _   |
  |  / \   / \   / \   / \  |
  | |   | |   | |   | |   | |
  |  \_/   \_/   \_/   \_/  |
  |                         |
  |    SpongeBob SquarePants   |
  |_________________________|