prabhanjana_c

I currently use the separate md file to capture the mermaid diagrams about the code, it helps to get overview of the file and various scenarios. It is good to keep all documentation ideally part of the same code. But if documentation is more as part of the code, passion to read source file is reducing, for me.

*_learnings.md: I am also using one more _learning.md, that captures what agents learn while building this file. it depends the complexity of the source file. mainly if the source files is about low level, protocols and so on. even separate _learnings.md also helps. so have now. _learnings.md may be needed how much investigation we have done to produce a working protocol.c.

protocol.c, protocol.md, protocol_learnings.md

spent 10 minutes watching and playing with. works in chrome. have issues in safari.

Interesting project. Works in chrome, I see safari, doesn't support, or have issues in my mac. It will be great to have a top level view , like flying in fortnight to have high level perspective.

WOW. I am curious to do the same for flute, mainly for Indian flute variations called Venu and Bansuri.

"To be honest, I’m sick to death of writing longform English to describe every change I want to my codebase. However, I also don’t want to go back to writing all my code manually."

I use voice input, when I get tired of typing, it is helping me really well. yes agree that, typing long form of English is very tiresome

Pseudocode -

- My question would be can it scale for all types of logic, and do we endup creating syntax similar to python.

Behaviour -

In the vibe coding , most of the time we also give behavior. I feel Gherkin syntax is best form to describe the behavior.

  https://cucumber.io/docs/gherkin/reference

actually too cool. very addictive, while changing different parameters and playing.

On my RTX3060 - 12GB VRAM + 24GB RAM , with below command

       ollama run qwen3.8:27b --verbose "explain mmap”, 

 I got  2.41 Tokens/s, Not sure if that can be improved considering VRAM doesn’t fit the entire, model.

Additional details:

total duration: 8m18.2870918s load duration: 612.105ms prompt eval count: 12 token(s) prompt eval duration: 2.900965s prompt eval rate: 4.14 tokens/s eval count: 1193 token(s) eval duration: 8m14.660618s eval rate: 2.41 tokens/s

System spec: NVIDIA GeForce RTX3060 AMD Ryzen 5 1600 Six-Core B450 AORUS M Mother board. NVIDIA-SMI 620.02 Driver:620.02, CUDA Version: 13.2

Great tried the Starboard.zip, opened in Dock, after given permission. it works. some caveats Cmd+E expands hight, but not width. also default width is may be around 4 to 5 characters. It think it may be related to auto hide property of dock. mine is MacBook Pro (macOS Tahoe version 26.5.1)

My workflow as of today is open a terminal at documents/claude_mac_master folder , with Claude Code cli. always running. this is my master for all frequent tasks.

frequent commands I use on that. - 1. open vscode for project with name (it searches and finds the matching folder and then opens the vscode, then onwards it remembers my top 10 projects or folders working on ), 2. move the recently downloaded images to right folder. 3. create a new experimental project with following vision, in the right folder, open it in cmux (another agentic terminal) , with vision.md so that I will continue to work on that. 4. check disk sizes, and any cleanup.

would like to run the any cli agent in this terminal with default operations.

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.

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 scaling laws, where at some point, it have interesting emerging properties, that nobody thought would be possible now being possible.

Tools: Though It is a tool, but powerfull tool that is automating existing manually done jobs, large scale. Adapting to new roles where we definite goals, needs and motives judging of AI output, at large level is an issue. And humans are used to day to day repeating job, doing same thing repeatedly. Now the AI is taking over that. I see that is a challenge.

Also I see we are moving to creative world, where we will spend more time on creating something really new, leaving mechanized parts to AI.

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.

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 aware, not being involved fully and not able to enjoy. spent few years like that, it is really difficult situation to be in. At some point, I realized, the self-awareness is towards emotions that are arising in myself, mainly, not on particular thoughts. means while speaking with others, if there is any strong emotion particular negative emotion raising in oneself. just being aware about that strong emotion actually cools down, and then it becomes a habit. and over a period of time along with emotion awareness also comes. and then we can still continue to enjoy the whole party.

It works, on my Mac book pro. Thanks!