News for hackers. Stuff that matters.
Re:LaVague: Open-source Large Action Model to automate Selen... by DanyWin on Wednesday March 13, 2024 @09:22PM (#39699650)
Thanks! Funny thing, we did not use Vision models but text only with the HTML of the current page. However, we intend to add it to boost performance
Re:LaVague: Open-source Large Action Model to automate Selen... by jerpint on Thursday March 14, 2024 @07:30AM (#39702521)
Interesting that it’s not vision based, I suspect you will get much better performance once vision is incorporated, using e.g LLaVa style models