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.
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.
Listen; we're not in a "Windows vs MacOS vs Linux user" meme. We're trying to have intelligent discussion here, and surely generalizing a large amount of people simply because they use one OS is not intelligent discussion.
Wake up. Real life is not what you see in funny memes.
I really like the Claude Chrome extension, but unfortunately it has too many limitations. Not only is it restricted to Chrome, but even within Chrome some websites especially financial ones are blocked.
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?
That’s true. The demo I showed was somewhat cherry-picked, and agentic systems themselves inherently introduce uncertainty. To address this, a possible approach was proposed earlier in this thread:
currently, after /teach is completed, we have an interactive discussion to refine the learned skill. In practice, this could likely be improved when the agent uses a learned skill and encounters errors, it could proactively request human help to point out the mistake. I think this could be an effective direction.
Interested, and disappointed that it's macOS only. I started something similar a while back on Linux, but only got through level 1. I'll take some ideas from this and continue work on it now that it's on my mind again.
One of the motivations for open-sourcing this is exactly to see it grow beyond macOS. I personally don’t have much development experience on Windows or Linux, so it’s great to see people picking up the idea and trying it on other platforms.
Interestingly, the original spark for this project actually came from my dad. He mostly uses CAD to review architectural design files, and there are quite a few repetitive steps that are fairly mechanical.Many operations don’t seem to be accessible through normal shell automation and end up requiring GUI interactions.
So one of the next things I want to try is experimenting with similar ideas on Windows, especially for GUI-heavy workflows like that, and see how far it can go.
sukhdeepprashut | a day ago
abraxas | a day ago
[OP] bayes-song | a day ago
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 | a day ago
Muhammad523 | 20 hours ago
Muhammad523 | 20 hours ago
renewiltord | 20 hours ago
You have all the tools.
jedreckoning | a day ago
sethcronin | 23 hours ago
[OP] bayes-song | 18 hours ago
rybosworld | 23 hours ago
mustafahafeez | 22 hours ago
[OP] bayes-song | 18 hours ago
walthamstow | 22 hours ago
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?
[OP] bayes-song | 19 hours ago
8note | 21 hours ago
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
[OP] bayes-song | 19 hours ago
obsidianbases1 | 21 hours ago
shawntwin | 11 hours ago
skeledrew | 19 hours ago
[OP] bayes-song | 18 hours ago
One of the motivations for open-sourcing this is exactly to see it grow beyond macOS. I personally don’t have much development experience on Windows or Linux, so it’s great to see people picking up the idea and trying it on other platforms.
Interestingly, the original spark for this project actually came from my dad. He mostly uses CAD to review architectural design files, and there are quite a few repetitive steps that are fairly mechanical.Many operations don’t seem to be accessible through normal shell automation and end up requiring GUI interactions.
So one of the next things I want to try is experimenting with similar ideas on Windows, especially for GUI-heavy workflows like that, and see how far it can go.