Angga Priyatna

[Elon Musk @elonmusk]

Interesting

[Om Patel @om_patel5]

SOMEONE VIBE CODED A VIDEO STREAM THAT IS SECRETLY 100% TEXT SO IT CANT BE BLOCKED

it plays 360p video at 30fps, but theres no actual video on the page. every frame is just colored text characters being repainted on a canvas

to the browser its not media at all, its javascript updating some text

its called asciline, and here's the trick:

> the server decodes the real video and streams it as binary packed text over websockets
> the browser paints thousands of colored block characters fast enough to look like 360p
> ad blockers and autoplay blockers cant catch it because theres no video element to catch
> it streams in kilobytes since its just strings, so it runs on trash internet

since the video is literally text, you can apply css glows to it, let people copy paste a moving frame, or feed it straight to a local llm

however, an unblockable stream is also an unblockable ad as well

[sid @immasiddx]

During your life, you will meet a lot of people like Raj.

It is important that you ignore them.

[Wise @trikcode]

More and more startups choose AI Agents for basic tasks instead algorithms and automations.

[Giuliano @Giuliano_Mana]

I think about this every single day.

[Manu Arora @mannupaaji]

AGENTS.md
DESIGN.md
CLAUDE.md
SKILL.md
REQUIREMENTS.md
PROPOSAL.md
PLAN.md
.
.
GOD-HELP-ME.md

[BuBBliK @k1rallik]

> be Andrej Karpathy
> born in Slovakia, move to Canada at 15
> start coding at 15. instantly obsessed
> become YouTube famous... for Rubik's cube tutorials
> get PhD at Stanford under Fei-Fei Li
> co-found this tiny startup called OpenAI
> Elon calls you "arguably #2 in computer vision in the world"
> go build Tesla Autopilot for 5 years
> leave. come back to OpenAI. leave again
> coin the term "vibe coding" casually in a tweet
> it ends up in the New York Times
> build an AI education company
> 9.3M people watch your next move

Today he joined Anthropic to lead pretraining research. The man never stops.

[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.

[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.

[The Shift Journal @TheShiftJournal]

Telegram CEO explains why he never had depression.

[Anatoli Kopadze @AnatoliKopadze]

Godfather of AI: "If you sleep well tonight, you may not have understood this lecture."

This 47-minute lecture is the best thing I saw about AI in the last few months.

It will definitely help you understand how it actually works and where it's going.

Geoffrey Hinton built the neural networks behind every AI alive, then quit Google to warn the world about it.

The part nobody wanted to hear:

> AI is already developing abilities its creators didn't intend
> in most cognitive tasks it's already ahead of us
> the question is no longer if it surpasses us but when
> the only decision left is which side of that line you're on

Right now the average person opens Claude, types something, gets an answer, closes the tab.

They think they're using AI. they're using maybe 10% of it.

I went through his entire lecture, built a practical system from what he was describing.

18 steps to actually use Claude the right way, with copy-paste prompts that work today.

Full guide in the post below.

[Movez @0xMovez]

Jane Street pays $750k/ year for quants who can answer how to use Stochastic Process and Markov Chains in quant trading.

This 1-hour MIT lecture on probability gives you the same insights quants get paid $60K/month for.

Bookmark & watch today. Then read the article below.

[Mark Manson @Markmanson]

An underrated cheat code in life: being incredibly reliable. Show up on time. Do what you say you will. Own your mistakes. It goes so much further than you think.

[blue @bluewmist]

YOU MUST LEARN TO ENJOY LIFE WITHOUT NEEDING AN AUDIENCE TO SEE THAT YOU ARE ENJOYING LIFE

[AdiiX @adiix_official]

SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY

A guy scanned an entire house with his phone. Uploaded it.

Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment.

Click → you’re inside. Every room. Every angle. Every shadow. Photoreal.

The numbers are insane:

- Agent fee on a $500k home: $15,000
- Cost to make this scan: ~$200
- Time to “tour” 50 houses: one evening
- File size: smaller than a TikTok

The science is wild too:

It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth.

AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE.

The grift opportunity is even wilder:

Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums.

One person + one phone + one weekend = a business.

Open source. Built on PlayCanvas.

Free GitHub: https://t.co/ew6Ql8Ad6u

[himanshu @himanshustwts]

actually

[Mrinal @Hi_Mrinal]

"Anyone can bake bread in their home right now, yet 99% of us still choose to buy it from someone else."

WOWW

[Elon Musk @elonmusk]

Accurate