People have been responding to emacs and my beard.

For a while I thought I did not have a lot to say. Turns out a lot of other humans are quite interested in the much of the same things that I’m into: my hatred for the mouse, and the consequent love for efficient workflows being some of them.

I’ll give the people what they want: I get to enjoy esoteric tech and spread the word, growing a cult, while other humans have enlightened experiences (believe me I do talk like this in person) and continue propogating the techno-propaganda about enjoying computer science.

From time to time, I do encounter ideas that intrigue my intellect for quite some time.
I do maintain the ideation buffer to index these ideas into the larger context of my past musings, but I would also like a conveniently accessible chronological search available for cross-domain ideas.
I’ll hence be increasing the frequency of premature technical thoughts being packaged into a micro-blogs.

I might not elaborate a whole lot in terms of the theoretical aspects of the tooling but I’ll be conceptually outlining my current thoughts over the same.

Writing is an involved process. A rough overview is as follows:

• you think of an idea
• you build upon that idea with what you already know
• you structure out some initial drafts
• you run it under a careful eye to scrape out the loopholes
• you edit it, to the point of satisfaction

The problem with that process is the last bullet right there. It makes the worth of a word in the moment diminish than the act of etching something down in stone.

Speech and the word written, are potential expressions of a thought. Each one of us enjoys a different mix of how we best convey ourself.

Ever since I began blogging when I was 19, I’ve been prioritising descriptiveness over precision. I feel I’ve entered a mental state where I value the distilled value of the transmission more than the exhaustiveness of the message.

I also notice a rift between the way I speak and the way I write. Not to say that any one of them is superior than the other but I could use an exercise in convergence - projecting them both onto a common ground.

To know thyself, is the beginning of wisdom
Socrates

On tangibility of the past

All of us create content, every moment, tuned to varying extents of influence and permanence.

It’s intent that separates us all into different leagues of producers.
Let me explain via a hierarchical build up of selected formats of content with varying intensity.
Note that the list isn’t exhaustive by any means and I’ve deliberately excluded works of larger scale (movies, video games : they have the potential to be the most influential kind of content out there).

The Premise

I was initially reluctant on using generative AI for my writing process.

That being said, I was quite aware of the potential of large language models (generically addressed as LLMs in here henceforth) - especially true in the case of content creators and/or eccentrically curious individuals.

I, therefore, decided to clarify how I’ll be using generative AI for my ideation process.

The Promise

Before we get onto that, as promised by the title, distilling the over-arching skills needed to extract good insights from a conversation with an LLM (an el-el-em; please don’t read it as large, please..).

So, I’ve been reading a book on prompt engineering and decided to practice a little…

Here’s a conversation I had with chatGPT regarding a small essay I wrote recently and fortunately, there’s room to improve.

Here’s how it went…

Criticize my writing …

Raj: You are my writing critic for this session; do not make any intellectual changes in any text I paste; do not heavily influence my style; only analyze what I say and generate pointers as to how I can become a better writer.

Books play a pivotal role in the life of any aspiring and existing intellectual. I began reading diversely and seriously when I was 19 and immediately regretted not starting sooner.

Reading sets you up for an involved existence. If you read vastly, you’ll be a force to be reckoned with.

Over the span of 3 years (2019 - 2022), I read around a 100 books ranging from the classics, biographies, auto-biographies, physics, computer science, anthropology, data science, etymology, theology, game theory, mathematics, history, how-to-books, nutrition, physiology , fitness, health, psychology, neuroscience, linguistics, business (okay, don’t judge - we all do this), economics, writing, self help (guilty as charged), spirituality, humor (guides to being funny and similar stuff), young adult (only 1 - please don’t chastise me - I could not handle the cringe), philosophy (a lot - please don’t chastise me) and meta books (speed reading, how to consume books, taking notes, etc).

This is an auxilliary post collating resources for the recent video I posted …

The Pipeline

1. All the ideas, resources that I want to process, any miscellaneous questions I have, are fed into the input-queue in the buffer
2. All the manipulation takes place in these buffers - they’re org-files and I use org-roam to maintain the connections
3. whenever a node set ripens and is worth sharing, I write a post or publish a video.
4. It can go both ways : I can force a set into maturity if I wish to publish something specific or I may chance upon a concept when observing connections.

Observations

I use org-roam-ui to visualize the buffer and check for linkages that might result in something useful. I also want to publish this graph (demonstrated in video) but there’s no explicit solution for that yet and I’m planning to build one myself with rust and webassembly as a compilation target.