Karpathy found a way to reduce token consumption by 90%
The problem is that the LLM re-reads the same files over and over again, loses context between documents, and provides less accurate answers as a result
The solution is called Wiki Layer the LLM cleans, structures, and links all your data once, after which it never works with raw files again
Three folders `raw/` for originals, `wiki/` for a clean knowledge base in Markdown, and files with rules for the agent
Result up to 90% token savings on repeat queries, automatic links between documents, and a visual knowledge graph in Obsidian
Everything stays on your local machine nothing goes to the cloud
In 13 mins, this video course will teach you how to build 3D websites for businesses in just 10 mins.
these websites sell for up to $10k. bookmark this, watch, build, and sell.
you’ll be using:
• claude code
• nano banana (free trial available)
the article below gives a step-by-step guide on how to use framer motion
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
Andrej Karpathy at YC AI Startup School:
"build Iron Man suits, not Iron Man robots."
i've been watching builders ship and builders stall. the shippers are still coding. they wear the suit. they direct a team of agents and the keys stay in their hands.
the stalled ones became the robot. they only prompt now. the muscle that catches when the model is wrong has gone quiet.
there is no neutral way to use AI. you either get sharper or you get hollower. most are getting hollower and won't notice till the chat won't open.
how to stay in the first group, inside:
This is how you become a control FREAK.
Ask your OpenClaw agent:
“Build me a fully comprehensive terminal for tracking events in real time (news + global events) based on this prompt.”
FULL PROMPT(bookmark): https://t.co/qwhmPSySMG
You’ll need a good events/news API. Personally I’d recommend:
> GDELT: massive global event intelligence database
> NewsAPI: simple and reliable real-time news feeds
Introducing https://t.co/nJkMOhuZ3c 🚨
The ultra-fast Linux-like OS in the browser, it's a mapping of Linux APIs to the browser APIs.
Now run that untrusted code. You might not need a cloud sandbox! Made for Agents and Humans!
My goodness...
Claude Code + Three JS is so much fun.
I created an interactive 3D room with interactive videos on the wall.
(Full Prompt to create this below 👇 )
Google just made a $2,000 AI education free (and most people will still choose to stay illiterate).
They quietly launched Google Skills, a hub with 3,000 technical modules that replaces "prompting" fluff with actual DeepMind research workflows. You can now access the exact curriculum used to train their internal teams on transformer architecture for $0.
If you don’t use this, you’ll eventually complain about the people who did.
If this is real, it’s incredible
(And they are total fools for posting it)
Using startlink latency, when satellites are overhead, to shave milliseconds off polymarket trades and be quicker than other bots
Similar to how stock trading firms build actual buildings near ISPs so the wires are shorter & they can trade faster
Im seeing a difference in behavior with deployed code on @Github pages vs the same files locally. Has anyone seen this before?
Left is edge generation run locally & right is on Github pages from one of my #threejs projects. Notice the extra lines.
1/3 👇
#webgl#javascript
oh my.. this is over for developers
Gemini 3 can create interactive 3D webpage in mins, just a few simple text prompts, it generates all the code
you can control millions of particles with your hands and make them form any shape you want
tutorial and prompts below:
Link: https://t.co/nfIquTmECN
I updated my #threejs portfolio to add some of my latest projects. Realistic water is now available in XR mode. The Mesh Transition material is available for purchase on Patreon. More projects are coming soon. Subscribe to the newsletter to stay up to date.
#threejsJourney #creativecoding #webgl #glsl
Trying to learn WebGL/Three.js but stuck on the math? 🤯
I made a course covering the 6 topics you need to know. Each has a theory lesson + interactive project (source code included!)
https://t.co/OqKK0FVOND
Here's a sneak peak 👀
I decoded Perplexity's ranking algorithm through browser requests. 59+ Ranking patterns exposed.
Found a configuration scheme + the near-exact config that controls visibility (tested & succeeded)
These findings might interest you
A THREAD 🧵👇 (1/n)