Viewing profile — ImPrajyoth
ImPrajyoth
HN member- Joined
- Thu, Jun 13, 2024, 10:41 AM UTC
- HN karma
- 59
- Public activity
- 32 items
- HN profile
- View on Hacker News ↗
About ImPrajyoth
No profile information was provided.
Recent public activity
-
comment
Comment #46487255
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 han…
-
comment
Comment #46487205
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 sec…
-
comment
Comment #46487178
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 …
-
comment
Comment #46453432
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 d…
-
comment
Comment #46445142
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!
-
comment
Comment #46442091
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 ac…
-
comment
Comment #46442083
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 …
-
comment
Comment #46435293
you are technically right (the best kind of right). i am running in userspace, so i cant replace the actual thread scheduling logic in Ring 0 without writing a driver and BSODing m…
-
comment
Comment #46435170
OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast …
- story
- story
-
comment
Comment #45756463
Isn't he the same person who wanted a Nobel peace prize few days ago?
-
comment
Comment #45598470
This! It's trying to be your helpful assistant, as engraved in its training. It's not your mentor or guru. I tried tweaking it to make my LLMs, both ChatGPT and Gemini, be as direc…
-
comment
Comment #45567314
>> Code/paper: [if public, otherwise say "available upon request for validation"] Atleast proof read before pasting
-
comment
Comment #45564925
This is glassmorphism, not liquid glass. Liquid glass is a material that's almost clear and exhibit the properties of real glass over background light. Glassmorphism is tinted glas…
-
comment
Comment #45382541
Earth is?
-
comment
Comment #45376615
Someone at open ai definitely said: Let's connect everything to gpt. That's it. AGI
-
comment
Comment #45376494
I’ve been tinkering with the last version for code gen. This update might finally put it on par with Claude for latency. Anyone tried benchmarking the new preview yet?
-
comment
Comment #45336627
Meant it as a joke on how fast we outsource our own voice—turns out the punch-line was me. Still, the dumb sentence got you to read the rest, so I’ll call it a successful typo.
-
comment
Comment #45336383
Yup, LLM ghost-wrote the dead article—kept it as digital mulch while I figured out publish buttons. First real post is the one you’re roasting. History will decide if that’s irony …
-
comment
Comment #45332941
50 M pesos on a wrist, Gini 51.3 in the stats — same weight. Rolex doesn't tick, it tracks the gap
-
comment
Comment #45332388
True. Watches were status symbols, but also everyone’s tool. Like a spoon—silver in one house, bent metal in another. Utility first. Status shows up only when the tool becomes a co…
- comment
- story
-
comment
Comment #45277634
It feels less of security related and and more of ecosystem lock-in related to be honest