Readit NewsI really like how easy it is to run using bunx, pnpx, npx, etc.
But does anyone have thoughts on the security aspect. Getting people used to just running code like this that has full access to the system is slightly concerning.
On the other hand it’s no different than installing npm packages
I look forward to a day when capabilities like this are trivial and boring to the average person. When my phone (locally) will be able to generate a fully voice acted 24 episode series anime on a whim for a meme with my group chat. It's astounding what we can do now, but will be completely ignorable before we know it, which is equally wild.
Who is going to spend time watching those episodes if content is so easy to make? Everyone will be busy watching their own generated content.
Will it learn that I don’t like ads?
It will figure out how to make ads that you do watch. If a generated video is good enough, people will watch it even though it’s an ad.
Later on a "live mode" which is realtime generated content, guided by your voice. Netflix could also have this as a feature.
The thing is that people don’t know or won’t say what they like.
The TikTok algorithm is good at figuring out what you do. Not what you say. So the content will be a lot more engaging.
The future is something like the TikTok algorithm, but generated on the fly.
As you scroll, it learns what you like and generates more videos.
How is the open-source voice assistant space these days? Is there a self-hosted alternative to Alexa these days?
Home Assistant is working on one
I’m working on a generic way of getting human input within any automated workflow.
The forms can be dynamically generated within the workflow, and then call back with the response.
The docs still need some work and I plan on adding some video demos, but here it is so far.
It has a pro over documented examples in that they are _guaranteed_ to be correct.