Because I need to develop a computer use tool


After messing around for a few days, I kept hitting walls when operating without an AX tree client framework (like QT) and mirroring the phone to perform some app operations
Then I tested some agents on the market that support Computer Use, and except for Codex, all of them performed poorly in these two aspects.
Basically, after opening the client, everything goes wrong, with all sorts of false successes
How exactly does Codex's Computer Use work? It's amazing 😭
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned