I wouldn't call it replacing the scheduler though - more that you've made a scheduler manager.
Scheduler Manager is definitely the more accurate term. Im just the middleman between the chaos and the kernel.
while BrainKernel replies: 'Objection overruled. You have 5 seconds to wrap up before SIGKILL.'
I might actually have to build a 'Process Defense Attorney' agent now. The logs would be hilarious.
But seriously, it does really bug me on principle that DropBox should use over half a GB simply because it uses Chromium, even when nothing is visible.
With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop.
i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or kills based on that.
Its my experiment in "Intelligent Kernels" how they would be. i used Delta Caching to keep overhead low.
And yeah - I was thinking that actually power efficiency isn’t really a massive deal if you have some kind of thin client setup. The LLM nodes can be at millraces or some other power dense locations, and then the clients are basically 5W displays with an RF transceiver and a keyboard…
An entertaining thought experiment :)
I think we are moving toward a bilayered compute model: The Cloud: For massive reasoning.
The Local Edge: A small, resilient model that lives on-device and handles the OS loop, privacy, and immediate context.
BrainKernel is my attempt to prototype that Local Edge layer. Its messy right now, but I think the OS of 2030 will definitely have a local LLM baked into the kernel.
Whether or not we'll see it lower down in the system I'm not sure. Honestly I'm not certain of the utility of an autonomous LLM loop in many or most parts of an OS, where (in general) systems have more value the more deterministic they are, but in the user space, who can say.
In any case, I certainly went down a fun rabbit hole thinking about a mesh network of LLM nodes and thin clients in a post-collapse world. In that scenario, I wonder if the utility of LLMs is really worth the complexity versus a kindle-like device with a copy of wikipedia...
Now that’s a cursed take on power efficency
If I burn a billion tons of someone else's coal to make myself a paperclip (and don't have to breathe the outputs) it works out in my favor too.
think of this more as a High-Level Governor. The NTOS scheduler decides which thread runs next, but this LLM decides if that process deserves to exist at all.
basically; NTOS tries to be fair to every process. BrainKernel overrides that fairness with judgment. if i suspend a process, i have effectively vetoed the scheduler.
This is a super simplification of the NTOS scheduler. It's not that dumb!
> if i suspend a process, i have effectively vetoed the scheduler.
I mean, I suppose? It's the NTOS scheduler doing the suspension. It's like changing the priority level -- sure, you can do it, but it's generally to your detriment outside of corner cases.
A 'Focus Mode' that doesn't just block URLs but literally murders the process if I open Steam or Civilization VI.
I could probably add a --mode strict flag that swaps the system prompt to be a ruthless productivity coach. 'Oh, you opened Discord? Roast and Kill.'
Thanks for the idea mate!
Sadly the only project I've found was for windows OS
If I'm AFK and it kills my IDE? I treat that as the system telling me to touch grass.