Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Replacing my OS process scheduler with an LLM

github.com

Post reply on HN
Print view View original

21–30 of 43 posts

Re: Show HN: Replacing my OS process scheduler with an LLM

#21

Post by redfloatplane »

ImPrajyoth wrote: post #9
2001zhaozhao wrote: post #7

It really is cursed to be spending hundreds of watts of power in a datacenter somewhere to make a laptop run slightly faster.

oh absolutely. burning a coal plant to decide if i should close discord is peak 2025 energy. strictly speaking, using the local model (Ollama) is 'free' in terms of watts since my laptop is on anyway, but yeah, if the inefficiency is the art, I'm the artist.

An interesting thought experiment - a fully local, off-grid, off-network LLM device. Solar or wind or what have you. I suppose the Mac Studio route is a good option here, I think Apple make the most energy efficient high-memory options. Back of the napkin indicates it’s possible, just a high up front cost. Interesting to imagine a somewhat catastrophe-resilient LLM device…

Re: Show HN: Replacing my OS process scheduler with an LLM

#22

Post by moffkalast »

devmor wrote: post #5

This is a pretty funny project, you've outsourced the neurotic developers that keep their task manager open and kill off processes they don't like. I wouldn't call it replacing the scheduler though - more that you've made a scheduler manager.

Assistant to the scheduler manager

Re: Show HN: Replacing my OS process scheduler with an LLM

#23

Post by GibbonBreath »

ImPrajyoth wrote: post #14
Agent_Builder wrote: post #13

[dead]

Great point. In a real kernel, non determinism is a bug. Here, it's a feature (or at least, a known hazard). To answer your question: There is no Ctrl+Z for SIGKILL. Once the LLM decides to kill a process, it's gone. My reasoning for 'rollback' is actually latency. I built in a 'Roasting Phase' where the agent mocks the process for a few seconds before executing the kill. That delay acts as an optimistic lock it give…

You're absolutely right. Being AFK is a sign of spending too much time at your computer.

Re: Show HN: Replacing my OS process scheduler with an LLM

#24

Post by QuantumNomad_ »

ImPrajyoth wrote: post #10
devmor wrote: post #5

This is a pretty funny project, you've outsourced the neurotic developers that keep their task manager open and kill off processes they don't like. I wouldn't call it replacing the scheduler though - more that you've made a scheduler manager.

haha exactly. i realized i spent too much time staring at htop wondering what is this process?, so i decided to automate my own anxiety. Scheduler Manager is definitely the more accurate term. Im just the middleman between the chaos and the kernel.

Now we need processes to gain awareness of the process manager and integrate an LLM into each process to argue with the process manager why it should let them live.

Re: Show HN: Replacing my OS process scheduler with an LLM

#25

Post by ImPrajyoth »

gillesjacobs wrote: post #18

You're underselling this as a process manager, it could also be a productivity tool with some prompt changes; Determine procrastination apps: games, non-professional chat, video streaming and kill it.

That is actually a brilliant pivot.

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!

Re: Show HN: Replacing my OS process scheduler with an LLM

#26

Post by ImPrajyoth »

QuantumNomad_ wrote: post #24
ImPrajyoth wrote: post #10

Earlier quoted context omitted.

haha exactly. i realized i spent too much time staring at htop wondering what is this process?, so i decided to automate my own anxiety. Scheduler Manager is definitely the more accurate term. Im just the middleman between the chaos and the kernel.

Now we need processes to gain awareness of the process manager and integrate an LLM into each process to argue with the process manager why it should let them live.

Imagine Chrome.exe pleading its case: 'Please, I need 4GB of RAM, the user might revisit that tab from 3 hours ago!'

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.

Re: Show HN: Replacing my OS process scheduler with an LLM

#27

Post by ImPrajyoth »

redfloatplane wrote: post #21
ImPrajyoth wrote: post #9

Earlier quoted context omitted.

oh absolutely. burning a coal plant to decide if i should close discord is peak 2025 energy. strictly speaking, using the local model (Ollama) is 'free' in terms of watts since my laptop is on anyway, but yeah, if the inefficiency is the art, I'm the artist.

An interesting thought experiment - a fully local, off-grid, off-network LLM device. Solar or wind or what have you. I suppose the Mac Studio route is a good option here, I think Apple make the most energy efficient high-memory options. Back of the napkin indicates it’s possible, just a high up front cost. Interesting to imagine a somewhat catastrophe-resilient LLM device…

That is the endgame.

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.

Re: Show HN: Replacing my OS process scheduler with an LLM

#28

Post by tryauuum »

ImPrajyoth wrote: post #25
gillesjacobs wrote: post #18

You're underselling this as a process manager, it could also be a productivity tool with some prompt changes; Determine procrastination apps: games, non-professional chat, video streaming and kill it.

That is actually a brilliant pivot. 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!

I was looking for a project which would run an LLM-powered character (like Clippy), who would periodically screenshot my screen and comment on my life choices.

Sadly the only project I've found was for windows OS

Re: Show HN: Replacing my OS process scheduler with an LLM

#29

Post by Xmd5a »

DougN7 wrote: post #8
devmor wrote: post #5

This is a pretty funny project, you've outsourced the neurotic developers that keep their task manager open and kill off processes they don't like. I wouldn't call it replacing the scheduler though - more that you've made a scheduler manager.

I resemble that comment! 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.

For me it's LSP servers taking 2 gigs of RAM. With Antigravity, Google managed to go beyond this, it is totally unusable for me (but other VScode clones work fine, apart from the 2 Go LSP servers).

Re: Show HN: Replacing my OS process scheduler with an LLM

#30

Post by redfloatplane »

ImPrajyoth wrote: post #27
redfloatplane wrote: post #21

Earlier quoted context omitted.

An interesting thought experiment - a fully local, off-grid, off-network LLM device. Solar or wind or what have you. I suppose the Mac Studio route is a good option here, I think Apple make the most energy efficient high-memory options. Back of the napkin indicates it’s possible, just a high up front cost. Interesting to imagine a somewhat catastrophe-resilient LLM device…

That is the endgame. 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.

Well, on my Macbook, some of that already exists. In the Shortcuts app you can use the "Use Model" action which offers to run an LLM on apple's cloud, on-device, or other external service (eg ChatGPT). I use this myself already for several actions, like reading emails from my tennis club to put events in my calendar automatically.

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...

Post reply on HN