...

...

[Om Patel @om_patel5]

THIS GUY LIVES UNDER SFO'S TAKEOFF PATH SO HE BUILT A CEILING PROJECTOR THAT TRACKS EVERY PLANE FLYING OVER HIS HOUSE IN REAL TIME

he uses a cheap $30 radio receiver to pick up the signals that planes broadcast while flying.

then projects them onto his ceiling in real time

when a jet flies over his house you hear it outside and at the exact same moment a plane glides across his ceiling labeled with the airline, aircraft type, and destination

pure black background so the projector's rectangle disappears and only the aircraft are visible

but he didn't stop at planes

it also draws the real sky behind them. sun, moon, bright stars, constellations, and live satellites including the ISS. all at their true positions for his exact location and time in real time

so he's lying in bed watching the actual night sky projected onto his ceiling with real planes crossing through it as they take off from SFO

there is a huge market for every man alive that runs outside to see the helicopter

vibe coded the whole thing himself with a cheap radio, a projector, and some clever software

[Melissa Chen @MsMelChen]

Singapore’s Foreign Minister, Dr Balakrishnan casually explaining how he built his own AI agent (a 2nd brain for diplomacy) using Claude & WhatsApp integration etc. on a Raspberry Pi

“You cannot govern a technology you have only been briefed on.” 🇸🇬

[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.

[Naval @naval]

Self-directed learning through AIs is an autodidact’s paradise.

[PiQ @PiQMarkets]

Just another day on the trading floor....

[Nathan Lands @NathanLands]

I'M BLOWN AWAY.

Andrej Karpathy just explained Software 3.0 at YC.

BIG IDEAS: English is coding. AI is electricity. And, build for LLMs, not just people.

Key takeaways:

[jack schwager @jackschwager]

Three traders that will be in next Market Wizards book currently being written (along with coauthor George Coyle @gfc4 ) are @Qullamaggie , @TheOneLanceB , @TheShortBear

[Matt Barrie @matt_barrie]

I was just interviewed by @EquityMates on the Australian economy. See if you can figure out what was censored 🤬😉
https://t.co/ijp7bR0ixu

[Doyle Brunson Legacy @TexDolly]

Today (10/2) we celebrate “Doyle Brunson Day.” Please enjoy this incredible, never before seen clip from his upcoming documentary. We invite you to share your own favorite @TexDolly stories here ⬇️

[Shane Oliver @ShaneOliverAMP]

Australia' top ten goods exports through time.

[HITMAN @GlobalHitman]

Probably the best introduction to golf ever.

[PaxTrader777🇺🇸 @paxtrader777]

@kaKrysinski @yaacov Leo Melamed was born in Bialystok. He is really a big hero of mine. I can’t stress how important he is to the modern world. He is certainly the reason we are traders. He is responsible for more than futures. He still trades ES every day

[Linda Raschke @LindaRaschke]

Jim Simons - how to beat the market in 5 minutes.
https://t.co/zTj83j7jnQ

[... @SenecaTrader]

The Art of Pepita | The fabric that became a Porsche classic https://t.co/MXu9qnsYUy

[Kevin Carpenter @kejca]

Charlie Munger: "You'd be amazed at how much I read. My children laugh at me. They think I'm a book with a couple of legs sticking out."

And he wasn't kidding. Here's an oldie of Charlie reading on the streets of London. $BRK.A $BRK.B

[The AI Investor @The_AI_Investor]

This is why computing has changed completely, and Nvidia is the only one GOT it.

Now: retrieval
Future: retrival + generation

[Massimo @Rainmaker1973]

The Bernina Express is a train connecting Chur (or Davos) in Switzerland to Poschiavo in Switzerland and Tirano in Italy by crossing the stunning Swiss Engadin Alps

[📹 Antonio Di Maiolo]

[Nassim Nicholas Taleb @nntaleb]

RIP, Charlie Munger
One of the last authentics.
WSJ, Mark Spitznagel, founder, Universa Investments:
"Munger was a guiding light that taught a generation (or two, or three) of investors, including me, how to think—what to focus on, what not to focus on, the importance of mental models, and how to avoid so much of the BS from the industry and academia."

[zerohedge @zerohedge]

*BERKSHIRE HATHAWAY SAYS CHARLIE MUNGER HAS DIED