Comment by teiferer

6 hours ago

No, tokenization is not the only reason. A next-word predictor has fundamentally a hard time executing algorithms, even as simple as counting.

Counting is one of the algorithms that can be expressed by a RASP program, which transformers closely approximate.

  • Close famously counts in horseshoes and hand grenades. Algorithms, just as famously, are a domain where off-by-one is still wrong.