News for hackers. Stuff that matters.

A comment on Bad numbers in the “gzip beats BERT” paper?. Parent comment

Re:Bad numbers in the “gzip beats BERT” paper? by thomasahle on Monday July 17, 2023 @09:31PM (#36766633)
These are good research topics, but then you really need to be comparing to other models in the same class.

The only other super cheap model they compare with is FastText, and FastText beat them quite substantially.

[ Parent | on HN ]
Re:Bad numbers in the “gzip beats BERT” paper? by westurner on Wednesday July 19, 2023 @01:36PM (#36790189)
Gzip fails at audio and video compression IIRC?

Are time-domain signals better compressed with A/V codecs (compression-decompression); and does this gzip finding suggest that other compression algorithms likely to outperform LLMs at certain tasks like computational complexity, at least?

[ Parent | on HN ]