TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Smaller Language Models Can Outperform LLMs

2 pointsby jasondrowleyabout 2 years ago

1 comment

joebiden2about 2 years ago
Suppose this was true, an extremely small language model would outperform small language models. Sounds like inventing a compression which compresses any input by at least one byte.<p>Sorry for the snark, but the linked article doesn&#x27;t explain why this obvious inference is false in this case.