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

11–20 of 43 posts

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

#11

Post by bdhcuidbebe »

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.

> using the local model (Ollama) is 'free' in terms of watts since my laptop is on anyway

Now that’s a cursed take on power efficency

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

#12

Post by ImPrajyoth »

bdhcuidbebe wrote: post #11
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.

> using the local model (Ollama) is 'free' in terms of watts since my laptop is on anyway Now that’s a cursed take on power efficency

efficiency is just a mindset. if i save 3 seconds of my own attention by burning 300 watts of gpu, the math works out in my favor!

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

#14

Post by ImPrajyoth »

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 gives me a window to veto the decision if I see it targeting something critical.

If I'm AFK and it kills my IDE? I treat that as the system telling me to touch grass.

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

#16

Post by abeyer »

ImPrajyoth wrote: post #12
bdhcuidbebe wrote: post #11

Earlier quoted context omitted.

> using the local model (Ollama) is 'free' in terms of watts since my laptop is on anyway Now that’s a cursed take on power efficency

efficiency is just a mindset. if i save 3 seconds of my own attention by burning 300 watts of gpu, the math works out in my favor!

"works out in my favor" is a pretty poor metric.

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.

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

#17

Post by SanjayMehta »

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.

Maestral is a cross platform implementation of the Dropbox client API which I use on low end Linux machines.

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

#20

Post by fragmede »

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.

Running ollama to compute inference uses energy that wouldn't have been used if you weren't running ollama. There's no free lunch here.
Post reply on HN