gpt_master
Re:Show HN: Skyvern 2.0 – open-source AI Browser Agent scoring 85.8% o...
on Tuesday January 21, 2025 @04:44AM (#42778131)
Very interesting. How are the evaluations done? i.e how do you categories a task as fail or success?
Re:General Purpose Web Agents on the Rise
on Thursday August 22, 2024 @09:15AM (#41319906)