Anthropic Computer Use - Hands On Tutorial

แชร์
ฝัง
  • เผยแพร่เมื่อ 11 ม.ค. 2025

ความคิดเห็น • 32

  • @animelover5093
    @animelover5093 2 หลายเดือนก่อน +6

    As the past few days , i am unwell and my motivation bit low , but right after seeing what Claude can do now , it has given me back my energy !! I will try to play around this thing on the weekend to explore

  • @nufh
    @nufh 2 หลายเดือนก่อน +11

    This is so wild. I mean, two years ago, something like this seemed impossible.

  • @dare2dream148
    @dare2dream148 2 หลายเดือนก่อน +1

    Thank you for sharing this so fast, Sam! I've got two qns: 1. Does it work on mobile devices? 2. How did you create the virtual environment to contain the risk?

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +1

      You can use Docker like I have show to contain the risk. I used the standard one they made in the vid. working on mobile is interesting. probably not on the device itself yet but on virtual mobile devices yes.

  • @BreeAiSolutions
    @BreeAiSolutions 2 หลายเดือนก่อน

    This is so good not so long ago i thought of this but with a lack of experience and knowledge atleast anthropic has done it ❤️but i still think this can also be done manually with the normal but its gonna take a lil bit longer ❤️these models are so intelligent man and thank you for sharing this Sam ❤

  • @wag6181
    @wag6181 2 หลายเดือนก่อน +4

    Does it solve captcha?

  • @dusanbosnjakovic6588
    @dusanbosnjakovic6588 หลายเดือนก่อน

    I built something like this using just their sonnet API and it was much slower and much more error prone. Any idea how it works under the hood and if there is any secret sauce on top of the API?

  • @PriteshSurale
    @PriteshSurale หลายเดือนก่อน

    is that posssible to use without docker and if possible how does model interact with our computer application?

    • @AlexGordon-j6u
      @AlexGordon-j6u หลายเดือนก่อน

      I think you cant use it directly to your local computer

  • @j4cks0n94
    @j4cks0n94 2 หลายเดือนก่อน +1

    Cool stuff. Can you share how much did it cost you for it to do the things it did in this video?

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +2

      I ran about 4 experiments and I think it was about $2

  • @montauk7250
    @montauk7250 2 หลายเดือนก่อน +2

    Amazing, I wish it didn't get rate limited so often

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน

      yeah totally. I think its better on GCP and perhaps AWS

  • @Chromiris-hj3sm
    @Chromiris-hj3sm หลายเดือนก่อน

    Rate limiting is a problem can anyone suggest a way to get around this with computer use?

  • @shakirabdo638
    @shakirabdo638 2 หลายเดือนก่อน

    Thank you ❤

  • @20windfisch11
    @20windfisch11 2 หลายเดือนก่อน

    Awesome, but I am waiting until local models can do that with ollama. I suppose this is going to get expensive fast when run on bedrock or GCP and Anthropic is rate limited too hard.

  • @vivekpraseed918
    @vivekpraseed918 2 หลายเดือนก่อน +1

    Is it as good as UIpath or Automation anywhere?

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +2

      would need to test it more, but my guess is with a bit more setup and prompt tuning etc you can make it much better. Certainly because is easier for people to use etc.

    • @vivekpraseed918
      @vivekpraseed918 2 หลายเดือนก่อน +1

      @@samwitteveenai Would open up a world of possibilities if it can be as good or better than RPA

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +3

      I kind of feel this is going to deliver, on what RPA promised 6 years ago. I saw UIPath back in 2018 at CloudNext and was really excited but it never seemed to deliver. Their stock price has tanked as well since going public which wasn't a great sign for them.

    • @vivekpraseed918
      @vivekpraseed918 2 หลายเดือนก่อน +1

      @@samwitteveenai Tried RPA a few years back..and since it wasn't working for my use case, had to develop my own solution that used CNNs to "see" the screen(worked almost flawlessly)...when multimodal LLMs came along, I kind of felt that eventually this would mean a swarm of reasonably intelligent agents getting together to accomplish very complex tasks... can't imagine how advanced it's all gonna get a decade from now

  • @vazox3
    @vazox3 2 หลายเดือนก่อน

    How expensive is the API e.g. the first task you Show, how much would this be in $?

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +1

      I did 4 examples and it was about $2 in costs

  • @LawrenceOrsini
    @LawrenceOrsini 2 หลายเดือนก่อน

    Other than actually working, how is this different than Ollamas pipelines and filters? It has access to more tools, yes, but what else?

  • @GrowithRohit
    @GrowithRohit หลายเดือนก่อน

    can we use google gemini sdk for python instead of anthropic and then we can use it for free

  • @finlay422
    @finlay422 2 หลายเดือนก่อน

    i wonder how this will effect web scraping bot detection.

    • @samwitteveenai
      @samwitteveenai  2 หลายเดือนก่อน +2

      scraping is getting easier and easier these days as long as you have good proxies

  • @fishraider7897
    @fishraider7897 2 หลายเดือนก่อน +1

    Damn, I'm scared for my job. Going to submit my unemployment paper tomorrow

  • @justinchen207
    @justinchen207 2 หลายเดือนก่อน +1

    dont forget to revoke ur key!

  • @fabriziocasula
    @fabriziocasula 2 หลายเดือนก่อน +1

    the api are to expensive

  • @zaidyounas1602
    @zaidyounas1602 หลายเดือนก่อน

    is this paid?