Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ks2048
on July 29, 2023
|
parent
|
context
|
favorite
| on:
Gzip beats BERT? Part 2: dataset issues, improved ...
Well put. Yes, I mention a similar case towards the end of that exchange: Consider a random-guess classifier. That has a
max accuracy
of 100%. Clearly, not a useful measure on its own.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
