alt Hacker NewsIt makes the world your canvas, but the device itself is intentionally screen-less. When you enter home - based on presence, time of day, ambient illuminance, barometric pressure, temperature what do you want to happen? Usually this involves a chain of devices, working together inside a blackbox running on an OS that no one single person can understand. What if all the cruft is abstracted away, and you can actually program and script in highly abstracted APIs what is going to happen. And that logic will last you for years. Or you tell an LLM and it writes the logic (code) for you. Having the logic run local makes the experience easier to reason about - now and in the future.
So yes, you can write code that calculates the angle of the sun and fire off a web request or email to send you an interesting HN link. But you can do much more...
[Edit] Again, this is only one approach that changes how we process input to reach a desired output.
Replies
> And that logic will last you for years.
A lot of desires that require computation might not be so "logical" in nature, at least not in the automation kind of things.
I use a lot of computing for entertainment purposes and leisure activities, like reading news/ebooks, watching shows/movies, listening to music, gaming, clothing/furniture shopping, going into all kinds of rabbit holes etc. The HN link from GP was such an example.
How could any automation through other physical input help there? Sure, there is vector similarity and recommendation engines, but how could any sensor interpret my aesthetics and my desires to belong/grasp/play/participate?
That sounds exactly like the empty sci-fi promises that current AI companies are betting on.
> When you enter home - based on presence, time of day, ambient illuminance, barometric pressure, temperature what do you want to happen? Usually this involves a chain of devices, working together inside a blackbox running on an OS that no one single person can understand.
A fair bit of this can already be implemented with a workflow that looks like:
Sensors -> zigbee or zwave -> home assistant
Or Internet based data -> home assistant (weather, external data, the humidity sensor at your local airport might be more accurate than the one on your deck, etc).
And then open source extensions/tools built into home assistant to cause things to happen, send external signals, run scripts, call APIs, talk to a local LLM, etc.
It's very much not a black box of opaque closed source software, rather the opposite, and it has a very active and technically knowledgeable enthusiast development community behind it.
If we posit for a minute that the data acquisition into locally-run system problem is not impossible to solve, then all kinds of things can be built atop that to serve your own unique home preferences.
> Having the logic run local
At the smallest scale people are doing this on raspberry pi, though I have seen people have much more satisfactory results on something with somewhat more system resources like an Intel N150 CPU based mini PC with 12GB RAM.
Going a bit up a bit in budget from there, people are running home assistant and frigate together on the same tiny system that is a KVM hypervisor (again all open source, no black boxes involved), so that Frigate can have a GPU passed through to it for image object detection/video analysis pipelines.