Can you save on LLM tokens using images instead of text? (pagewatch.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of pagewatch.ai: Can you save on LLM tokens using images instead of text?

First screen, captured 11 months ago.

Looks similar

Screenshot of seangoedecke.com: Should LLMs just treat text content as an image?

Should LLMs just treat text content as an image?(seangoedecke.com)

159 points by ingve 1 year ago | 94 comments

Screenshot of ngrok.com: Prompt caching for cheaper LLM tokens

Prompt caching for cheaper LLM tokens (ngrok.com)

268 points by samwho 10 months ago | 67 comments

Screenshot of declaude.org: How AI text watermarking works

How AI text watermarking works (declaude.org)

86 points by padolsey 2 months ago | 59 comments

Screenshot of seangoedecke.com: Why DeepSeek is cheap at scale but expensive to run locally

Why DeepSeek is cheap at scale but expensive to run locally (seangoedecke.com)

299 points by ingve 1 year ago | 176 comments

Screenshot of lmsys.org: How long can open-source LLMs truly promise on context length?

How long can open-source LLMs truly promise on context length?(lmsys.org)

174 points by dacheng2 3 years ago | 58 comments

Screenshot of nelson.cloud: AI-Generated Images Discourage Me from Reading Your Blog

AI-Generated Images Discourage Me from Reading Your Blog (nelson.cloud)

12 points by nelsonfigueroa 1 year ago | 1 comments