2

I suspect GPT-4's performance is influenced by data contamination, at least on C...

 1 year ago
source link: https://twitter.com/cHHillee/status/1635790330854526981
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

Conversation

I suspect GPT-4's performance is influenced by data contamination, at least on Codeforces.

Of the easiest problems on Codeforces, it solved 10/10 pre-2021 problems and 0/10 recent problems.

This strongly points to contamination.

1/4

Image
Image
Quote Tweet
4rqdxVqQ_mini.jpg
Horace He
@cHHillee
Mar 14

How is it even … possible to have a codeforces rating of 392? That’s very low.

Like, my understanding was as long as you participated in a couple of contests (regardless of how you did), you'd have a rating above 392. twitter.com/OpenAI/status/…


report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK