Viewing profile — prabhanjana_c
prabhanjana_c
HN member- Joined
- Tue, Jun 23, 2026, 11:49 AM UTC
- HN karma
- 7
- Public activity
- 27 items
- HN profile
- View on Hacker News ↗
About prabhanjana_c
Recent public activity
-
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…
-
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…
-
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.
-
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…
-
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…
-
comment
Comment #49080924
It works, on my Mac book pro. Thanks!
-
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 …
-
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.
-
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…
-
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/…
-
comment
Comment #49025413
Concept is good. It will be good to try without getting logged in, just to taste. or with a guest login.
-
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…
-
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.
-
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.
-
comment
Comment #49002470
Just heard the Scheme Programming language. Great to know that.
-
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…
-
comment
Comment #48978502
Clean and simple UI. Some glitches on iPad. Would like to experiment on iPad.
-
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.
-
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.
-
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…
-
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…
-
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…
-
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…
-
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?
-
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…