11 comments

  • obsidianbases1 8 minutes ago

    Nice work. I scanned through the code and found this file to be an interesting read https://github.com/understudy-ai/understudy/blob/main/packag...

  • rybosworld 2 hours ago

    I have a hard time believing this is robust.

  • 8note an hour ago

    sounds a bit sketch?

    learning to do a thing means handling the edge cases, and you cant exactly do that in one pass?

    when ive learned manual processes its been at least 9 attempts. 3 watching, 3 doing with an expert watching, and 3 with the expert checking the result

  • walthamstow 2 hours ago

    It's a really cool idea. Many desktop tasks are teachable like this.

    The look-click-look-click loop it used for sending the Telegram for Musk was pretty slow. How intelligent (and therefore slow) does a model have to be to handle this? What model was used for the demo video?

  • sethcronin 3 hours ago

    Cool idea -- Claude Chrome extension as something like this implemented, but obviously it's restricted to the Chrome browser.

  • abraxas 5 hours ago

    One more tool targeting OSX only. That platform is overserved with desktop agents already while others are underserved, especially Linux.

    • bayes-song 5 hours ago

      Fair point that Linux is underserved.

      My own view is that the bigger long-term opportunity is actually Windows, simply because more desktop software and more professional workflows still live there. macOS-first here is mostly an implementation / iteration choice, not the thesis.

    • renewiltord 5 hours ago

      That's mostly because Mac OS users make tools that solve their problems and Linux users go online to complain that no one has solved their problem but that if they did they'd want it to be free.

  • mustafahafeez 2 hours ago

    Nice idea

  • jedreckoning 5 hours ago

    cool idea. good idea doing a demo as well.

  • sukhdeepprashut 5 hours ago

    2026 and we still pretend to not understand how llms work huh