Did you check MiMo correctly performed this unfamiliar task before posting this comment?

I did. I read the code to make sure the quality of MiMo's work matched mine for a quick experiment, though not that the code was free from subtle bugs.

This was the main change for bzip2:

  @@ -33,19 +34,16 @@ def candidate_lengths(
       level: int = 9,
       pool: ThreadPoolExecutor | None = None,
   ) -> list[int]:
  -    """Compressed length of ``context + seq`` for each seq, sharing the context.
  +    """Compressed length of ``context + seq`` for each seq.
  
  -    Compresses ``context`` once into a ``compressobj``, then clones its encoder
  -    state per candidate and feeds only that candidate. Identical to
  -    ``len(zlib.compress(context + seq, level))`` for each seq, but the expensive
  -    match search over ``context`` happens a single time.
  +    Unlike ``zlib``'s ``compressobj``, Python's ``BZ2Compressor`` cannot be
  +    snapshotted mid-stream, and bzip2's move-to-front + Huffman stages see the
  +    whole block, so every candidate recompresses the full context. Threads
  +    still scale because ``bz2`` releases the GIL.
       """
  -    base = zlib.compressobj(level)
  -    head = len(base.compress(context))
  
       def length_for(seq: bytes) -> int:
  -        clone = base.copy()
  -        return head + len(clone.compress(seq) + clone.flush(zlib.Z_FINISH))
  +        return len(bz2.compress(context + seq, level))
  
       if pool is not None:
           return list(pool.map(length_for, sequences))

Is the fact that the original did [compress base]+[compress seq] rather than [compress [bytes + seq]] not important?

(I honestly don’t know is gzip does something different when presented with two chunks as opposed to one, or, if it does, if bz2 has equivalent behaviour - but the difference in the code did stand out to me, and it does seem related to ‘extending the token sequence’)

This difference doesn't matter because of how zlib works. At least by default, zlib divides the input data into its own blocks independent of the caller. If you don't feed it enough data to complete a block, it waits until you feed it more or finish the stream.

We can test it by going back to zlib:

       def length_for(seq: bytes) -> int:
  -        return len(bz2.compress(context + seq, level))
  +        return len(zlib.compress(context + seq, level))

At temperature zero, this outputs the same sample as commit 3734bf6, the most recent commit upstream:

  MENENIUS:
  'Though all at once cannq

  MARCIUS:
  I'll fight
  'Though all at once cannq

  MARCIUannq
  
  MARCIUS:
  I'll fight
  'Though
  
  AUFIDIUS:
  If I fly, Marci
  
  AUFIDIUS:
  If I fly, Marci
  
  AUFID
  
  AUFIDIUS:
  If
  If I fly

I also tried LZMA for good measure:

       def length_for(seq: bytes) -> int:
  -        return len(bz2.compress(context + seq, level))
  +        return len(lzma.compress(context + seq))

The sample at temperature zero:

  MENENIUS:
  'Th
  
  A carbuncle enti
  
  , as big as thou
  
  
  A aa

This is followed by a lot of whitespace.

python-lz4 gives you all newlines after the prompt. I tried debugging it, and the compressed length of different candidate seqs is the same.

So, you had an AI write code you don't understand, then posted output you don't understand in a comment on the internet for other humans to read?

No, they used AI to write code they do understand, then posted interesting results they (partially) don't understand for other humans to see.

Then why attribute the work to MiMo? People mostly only attribute the model when they've outsourced the understanding along with the coding. If I understand the code I don't bother to mention the tools I used to create it.