Live data from Hacker News

Viewing profile — prabhanjana_c

prabhanjana_c

HN member
Joined
Tue, Jun 23, 2026, 11:49 AM UTC
HN karma
7
Public activity
27 items

About prabhanjana_c

Embedded Application Architect, ~25 years. Now building AI-based developer tools at TURYON Tech Labs. turyontech.com

Recent public activity

  1. comment
    Comment #49206233

    Cool, good project. tried it works. I think it will have great experience, along with voice mode, where I can talk, like in voice mode of chatgpt, while also practicing in notebook…

  2. comment
    Comment #49182886

    Calculator for language, is a nice insight. I visualize generally as LLM's as big mathematical expression that produce next word. But then , one difference I found on LLM's is on s…

  3. comment
    Comment #49143975

    useful project. it will be good, if it supports prompts too. as if, I can chat with the kernel to understand it. may be be with local model or something like that.

  4. comment
    Comment #49134076

    Recently I heard a term "Software factory" - I am strongly rooting with this term, particularly while working with agents and AI. Heard from Vercel, Guillermo. "The (software) fact…

  5. comment
    Comment #49133962

    Resembled with above experience. Wanting to be self aware, I spent couple of years in confusion. Rather only thinking about what I am doing at any point of time, and trying to be a…

  6. comment
    Comment #49080924

    It works, on my Mac book pro. Thanks!

  7. comment
    Comment #49080858

    Great, just experimenting to see which is better voice apps to use for my Claude Code cli, on my Mac. for now settled with /voice command. will try Yap. It will be good to have an …

  8. comment
    Comment #49080713

    At least recognizing that we hold simplified model of the world, and knowing that it is limited, is a reasonable place to be in and that helps to explore more.

  9. comment
    Comment #49049261

    Interesting to see the rust code is doing the actual parallelization, while execution. Will it work for complex loops, and what happens if the loops uses global context and differe…

  10. comment
    Comment #49025527

    Interesting. Still wondering how this is different from a structured app building with let us say https://github.com/github/spec-kit , or using some skills from https://github.com/…

  11. comment
    Comment #49025413

    Concept is good. It will be good to try without getting logged in, just to taste. or with a guest login.

  12. story
    Show HN: Chrome Plugin to Scan HN Page Quickly. (Categorize with Local Model)

    Recently I started spending more time reading HN posts, and engaging. Wanted to scan HN pages faster ,that rosonates to me. For me it is easy to grasp if they are in the order of s…

  13. comment
    Comment #49016343

    Thanks! Seems actual code for interpreter is in https://github.com/virtualagc/virtualagc/blob/master/Luminar... . I see it is different for each revision/module.

  14. comment
    Comment #49002636

    Nice view with sector wise grouping. while browsing independent nodes in one galaxy if the graph doesn't move, it will distract less I think.

  15. comment
    Comment #49002470

    Just heard the Scheme Programming language. Great to know that.

  16. comment
    Comment #49002446

    Great to see the AGC assembly code and knowing that Apollo 11 is coded purely in assembly. Not sure if it has any compiler. Also found https://github.com/virtualagc/virtualagc whil…

  17. comment
    Comment #48978502

    Clean and simple UI. Some glitches on iPad. Would like to experiment on iPad.

  18. comment
    Comment #48977477

    Curious to understand , if this can be added as a skill to claude code cli /goal along with. I see it supports claude code agent sdk.

  19. comment
    Comment #48955132

    Nice and simple UI. I am new to electrical grid, and always curious to understand, overall grid and how it operates. Seems this is good starter.

  20. comment
    Comment #48950036

    Quite cool. Experimented it works. Nice to see each chip behavior is emulated. Wondering how does it make sure simulated chip is really behaving, the way real hardware behaves. Goo…

  21. comment
    Comment #48930510

    Great, yes with samosa app can see details, it is 6.52tok/sec, 4.05GB memory. Use case, I have been waiting was to run some agents in my Mac continuously with local models, but wit…

  22. comment
    Comment #48923284

    Actually quite cool. My mac is not getting heated. will check more. Memory pressure is very low. I see it (memory used) just increased from 22GB to 27Gb(on 48GB pro), while using s…

  23. comment
    Comment #48916647

    Very interesting. I am always curious on llama.cpp and vllm. All the best for samosa inference engine. One reason I am not running local models on my Mac now a days, is My Mac book…

  24. comment
    Comment #48916545

    Interesting project. Will try sometime, on a call. Does the installed agent work only with agentcall service. Can it work with any other voice api?

  25. comment
    Comment #48907654

    UI is clean. could install in Mac. Adding context files at the top is clean. It worked. Currently I use zed, vscode (for UI). along with claude, codex, Hermes. Not sure If I will c…