Hacker News new | ask | show | jobs
Show HN: WebMarker – Mark web pages for use with vision-language models (webmarkerjs.com)
2 points by reidbarber 508 days ago
WebMarker is a JavaScript library used for adding visual markers and labels to elements on a web page. This can be used for Set-of-Mark prompting, which improves visual grounding abilities of vision-language models such as GPT-4o, Claude 3.5, and Google Gemini 1.5. This library aims to:

- Improve LLM performance on vision tasks referencing web pages - Enable reliable web page interactions based on LLM responses

1 comments

I think that omniparser is better for this