Pranesh Pyara Shrestha 🇳🇵

23, Engineer

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

Like Vincent Van Gogh, he dedicated his life to his art and lost his mind in the process. When everything pays off and when my mother has a big mansion, when my family has a different car for every day of the week-

[Jay Alto @theJayAlto]

laying bricks isn't mundane when you know you're building a cathedral

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

@princi_koirala You mean develop a separate regulatory framework for this Starlink ignoring the Telecommunication Act of Nepal?Currently, FDI is capped at 80% of the total, and a minimum of 20% must remain with domestic shareholders. Full foreign ownership in telecom domain isn't good either.

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

@nirajbhusal Could have been integrated with nagarik app. Also the UI is so basic, like made by someone who is just learning flutter

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

for non-tech friends, its like John Cena joining AEW

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

If you are doing one chat session per chapter, this will be much organized. I often find this method very helpful.

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

A pro tip for someone who makes notes with ChatGPT or Gemini or any other tools(and has no premium subscription).

Copy everything from that chat session. And instruct claude to export that into markdown file. And convert that into a pdf using any (md to pdf converter).

[Andrej Karpathy @karpathy]

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.

More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage:

1) raw text (hard/effortful to read)
2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default
3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default
...4,5,6,...
n) interactive neural videos/simulations

Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral https://t.co/z21CP5iQfu

There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen.

TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

@HimalayaAILabs Any benchmarks?

[kache @yacineMTB]

you can outsource your thinking
but you cannot outsource your understanding

[staysaasy @staysaasy]

The degree to which you are awed by AI is perfectly correlated with how much you use AI to code.

[le.hl @0xleegenz]

Walking alone through a foreign city at night and realizing how far you’ve come has to be a top 3 peak moment of all time

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[John Cena @JohnCena]

Refuse to be defined by a single accomplishment.

[John Cena @JohnCena]

No one knows their ultimate ceiling for achievement, so worrying about it might not be the best allocation of resource.

[Claude @claudeai]

You can now enable Claude to use your computer to complete tasks.

It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk.

Research preview in Claude Cowork and Claude Code, macOS only.

[y @ysuckme]

A moving man will one day meet his luck. The road favours a traveller.

[27. @dimvji]

'a moving man will surely meet his luck’ has to be the realest quote i’ve ever heard

[Prasenjit @Star_Knight12]

to keep up with AI, you need to be unemployed

[Pranesh Pyara Shrestha 🇳🇵 @PraneshP1Org]

@claudeai Me after hearing HR industry is going to be cooked as well

[WWE @WWE]

AJ Styles is OFFICIALLY a member of the WWE Hall of Fame Class of 2026! 😤

@AJStylesOrg