This was really simple to use with Docker! And I felt more safe playing around with it in that space... what are your thoughts on Claudes new Computer Use feature that controls your computer? I think it has potential to be really useful for coding, productivity, video editing etc.. but still has a long ways to go.
I tried it tonight following your tutorial, waste of time, 6 actions cost me 0.29 Euro, also the job was simple and easely reproduced by micro programming, this was slow and overly expensive. I think they were making this a big news, but it is actually nothing that the current tech cannot replace.
Tiff, your honesty is refreshing, thank you all those other gurus are talking about how great this works, it does not, as you said it has a long way to go....
Navigating the setup and rate limitations you mentioned truly highlights the push-pull of AI development. Early adopters like yourself help pave the way for more seamless use in the future. Thanks for sharing the experience!
I think I might find this helpful at this level of capability! I developed my own "computer use" tool shortly after function calling became a thing. Just an experiment. It used screenshots, OCR + screen-coord data to orient the LLM and give it context. But... it was pretty limited. Fun watching it move the mouse around, click, search, open apps, open terminal, type, etc. but it could not interact with much beyond basic/core windows interactions. Plus, it would stop randomly, click the wrong buttons, shut down my computer, etc. This is far better.
This seems like a great tool for accessibility, especially if in the future you could dictate your command via voice input. One thing to make it even better is if you could give it commands while having another program/window open and you continue working on your program while you have the agent perform another task for you in the background. This way you aren't just waiting for it to finish for you to do something, you can have it perform a task in parallel. I assume this is difficult because it takes screenshots of your screen to perform tasks, so if you are also using the screen for something else and using the mouse and keyboard for something else, it make cause issues, but there should be ways via software to have 2 mouse cursors at once and hide your "active" window from what the agent sees. Having 2 users on the same computer with different mouse and keyboard input has been done many years ago, so this doesn't seem like such a difficult ask, hopefully we can see something like this with future versions.
I'm not surprised you were rate limited. Other sources have told me this flies through tokens so quickly. The potential is great but it really reminds you how much processing power it takes to do things we take for granted.
that was 1 minute and 42 seconds, not 1 hour 42 minutes, but you are right, it was released to the wild a tad bit early! hope you are enjoying Dublin regardless!
Thanks Tiff, very cool. I loved the simplicity of the Docker instance the most. Al Swegart in his Automate The Boring Stuff With Python has an interesting Python web automation example, which looks similar to what Anthropic is tapping. Lots of course curation potential in this future application I think.
It'll be super cool if this could be fine tuned or provided additional functionality/ streamlining for working with cumbersome tools like spreadsheets. I guess it is open source so I guess it's on us to do that!
What they're not telling you is it's worthless due to rate limits. Do not factor Claude into major applications - Claude is a novelty gimmick thingy that's all it is. Premium membership was money wasted I would have gotten more value out of a TikTok filter.
So easy to set up but, so far all the requests are saying Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'messages.6: Did not find 1 tool_result block(s) at the beginning of this message. Messages following tool_use blocks must begin with a matching number of tool_result blocks.'}}
If that can help, the command didn't work for me, I had to ask chatGPT to change it to paste using cmd on windows ('set' instead of 'export' first, then paste the rest with '^' instead of '\')
This was really simple to use with Docker! And I felt more safe playing around with it in that space... what are your thoughts on Claudes new Computer Use feature that controls your computer? I think it has potential to be really useful for coding, productivity, video editing etc.. but still has a long ways to go.
I tried it tonight following your tutorial, waste of time, 6 actions cost me 0.29 Euro, also the job was simple and easely reproduced by micro programming, this was slow and overly expensive. I think they were making this a big news, but it is actually nothing that the current tech cannot replace.
Tiff, your honesty is refreshing, thank you all those other gurus are talking about how great this works, it does not, as you said it has a long way to go....
Navigating the setup and rate limitations you mentioned truly highlights the push-pull of AI development. Early adopters like yourself help pave the way for more seamless use in the future. Thanks for sharing the experience!
I think I might find this helpful at this level of capability!
I developed my own "computer use" tool shortly after function calling became a thing. Just an experiment. It used screenshots, OCR + screen-coord data to orient the LLM and give it context. But... it was pretty limited.
Fun watching it move the mouse around, click, search, open apps, open terminal, type, etc. but it could not interact with much beyond basic/core windows interactions. Plus, it would stop randomly, click the wrong buttons, shut down my computer, etc.
This is far better.
This seems like a great tool for accessibility, especially if in the future you could dictate your command via voice input.
One thing to make it even better is if you could give it commands while having another program/window open and you continue working on your program while you have the agent perform another task for you in the background. This way you aren't just waiting for it to finish for you to do something, you can have it perform a task in parallel. I assume this is difficult because it takes screenshots of your screen to perform tasks, so if you are also using the screen for something else and using the mouse and keyboard for something else, it make cause issues, but there should be ways via software to have 2 mouse cursors at once and hide your "active" window from what the agent sees. Having 2 users on the same computer with different mouse and keyboard input has been done many years ago, so this doesn't seem like such a difficult ask, hopefully we can see something like this with future versions.
Hello Everyone.....I use the Ai agent daily and I'm very happy to use this tool
I'm not surprised you were rate limited. Other sources have told me this flies through tokens so quickly. The potential is great but it really reminds you how much processing power it takes to do things we take for granted.
Yep. AI is a little bit cluttered in terms of its knowledge set. A lot of inefficiencies
Yeah, it reading those screenshots uses a ton of tokens
that was 1 minute and 42 seconds, not 1 hour 42 minutes, but you are right, it was released to the wild a tad bit early! hope you are enjoying Dublin regardless!
Your advices are always useful. I was heard about but now I have notice how so great tool is it. Cheers Tiff!
Thanks Tiff, very cool. I loved the simplicity of the Docker instance the most. Al Swegart in his Automate The Boring Stuff With Python has an interesting Python web automation example, which looks similar to what Anthropic is tapping. Lots of course curation potential in this future application I think.
you promised 'links down below' for some things that do not appear 'below'
Thanks for teach and share!!! Blessings
GREAT VIDEO!
Thank you
It'll be super cool if this could be fine tuned or provided additional functionality/ streamlining for working with cumbersome tools like spreadsheets.
I guess it is open source so I guess it's on us to do that!
Welcome to Dublin!
What they're not telling you is it's worthless due to rate limits. Do not factor Claude into major applications - Claude is a novelty gimmick thingy that's all it is. Premium membership was money wasted I would have gotten more value out of a TikTok filter.
So are using the paid version? Have you figured out why is failed so quickly... i saw another video where it worked almost flawlessly.
3:21 starts here
So easy to set up but, so far all the requests are saying Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'messages.6: Did not find 1 tool_result block(s) at the beginning of this message. Messages following tool_use blocks must begin with a matching number of tool_result blocks.'}}
If that can help, the command didn't work for me, I had to ask chatGPT to change it to paste using cmd on windows ('set' instead of 'export' first, then paste the rest with '^' instead of '\')
What’s the app builder called?
cannot hear much because of that music, bass etc
hey tiff, musics too loud hard to follow along
First comment
Yayyy! Hope youre having a great day!!
Music too loud, too distracting.
It is not free ???
1st view 🎉❤tiff
You're the best! Hope your week is off to a great start!!
Wow that is not a bad first try. Lol geez
🔥🔥😮
Happy Tuesday!! Have you tried this out before?!
@@TiffInTech Not yet tiff! Definitely I will try! How smoothly are you running it on Docker container 🔥🐋
I have heard about Claude new AI but not in depth
Its super interesting! Their new feature I think has a lot of potential
3:23. 4:13
i think I'm actually in love with you, are you married?
What waste of my time watching the video