Claude Code creator:
"100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too.
The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops"
in this interview he breaks down exactly how a system changes everything:
- the memory and context features that turn Claude into a second brain
- the knowledge architecture most users don't know Claude can build
- the integration layer that connects Claude to your actual workflow
- why typing one question at a time is the most expensive way to use Claude
if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
full guide in the article below
A normal American student just bought an iPad and Mac Mini for $2,200. Connected them to his MacBook.
Three computers on one desk - dorm roommates thought he was mining crypto.
He just set up the automation and went to sleep.
In the morning the system had already processed hundreds of leads, written personalized emails to each one and filled the CRM without a single touch.
The team that did this before him- cost $7,000 a month
He paid $2,200 once.
There are 360 million companies in the world and 310 of them still pay people for what a machine does better.
And only 100,000 people on the planet know how to use AI and set this up.
This is the best site on the internet to learn how LLMs actually work.
Free. Completely.
https://t.co/YOGF6PsmBN
Bookmark this site.
Then read this setup ↓
probably the best blog i have read for some time
viewing SFT, RL, and OPD as different ways of reshaping a model's distribution makes their tradeoffs super intuitive.
- SFT pulls toward a fixed external target
- RL moves along the reward gradient on on-policy samples
- OPD sits in between, using a teacher signal but on student-generated data, which is why it inherits RL's anti-forgetting properties even when the teacher itself was an overtrained SFT model.
the post is heavily grounded in recent literature and uses the distributional perspective as a unifying bridge across all three paradigms, i really like the point it argues the load-bearing ingredient is on-policy data and OPD's convergence to RL-like outcomes is the strongest evidence
My talk at MIT, on "Agentic AI systems: from scruffy to neat", is now available. I cover 3 examples of agentic systems - Bayesian linguistic forecaster, autoharness, and code world models - which combine LLMs, code and planners in different ways. Links below.
After interviewing for Research Scientist roles at DeepMind, Isomorphic, Meta, Cohere and more, I wrote up everything I learned. Technical prep, logistics, negotiation, and emotional breakdowns. Check out my guide: https://t.co/eLh20ggMHW
tired: introspection (reflect on your relationships)
wired: whooptrospection (download your wearables data, cross reference with face time for everybody in your life, give the whole thing to Claude Code, make a biometric matrix of interpersonal calmness, export to Excel, reverse rank by heart rate, “Siri ask whoever’s at the top of column C to come over for beers to watch game 4”
omg omg omg this is blowing up 😭😭 I just love building stupid fun weird projects purely for the joy of it
if that’s your vibe, I’m sure you’ll have fun exploring my profile and projects
most of them live here
https://t.co/sWoIAZmRcr
i hooked my whoop to my work calendar to find which coworker gives me the most stress 🚨
thanks to fable, I reverse engineered whoop to pull per minute heart rate. nd matched spikes with cal events and attendees
I now have a leaderboard and I think about it daily.
few info masked for obvious reasons ;)
Howard Marks has been writing investment memos for 30 years that Warren Buffett says he reads first thing every time.
In 36 minutes he explains why every bull market ends the same way - and where he thinks we are right now.
36-min. Oaktree. TBPN.
Bookmark & watch - the clearest market cycle read you'll find in 2026
Pankaj Tibrewal on stock picking during bad cycles:
When earnings are under stress, don't focus only on the P&L.
Go into cash flows.
If free cash flow yield reaches 5-6% and the balance sheet isn't broken, just go and buy those businesses.
2 minutes of pure Gold !!!🔥
A broccoli farmer in Hokkaido is managing his entire 100-hectare farm using Codex. And he's never written a line of code in his life. 🤯
10 years ago this guy was a civil servant in Tokyo. No farming background. No inherited land. No engineering degree. Just curiosity.
Today he controls his greenhouses from a chat app on his phone.
A bot monitors temperatures and opens the vents automatically. Satellite data shows him which crops are healthy and which need attention.
His entire operation fields, workers, tasks, sensors runs through a database he built himself.
He even takes photos of his electrical panels and AI generates the wiring diagrams for him.
All of this used to be locked behind expensive machinery and engineers that only the biggest farms could afford.
This guy did it with a $5 microcontroller, a laptop, and Codex.
He now does ¥100 million in revenue. OpenAI flew him out to their Tokyo office.
Everyone talks about AI replacing jobs.
Nobody talks about the farmer in rural Japan who used it to build something nobody thought he could.
If you want highly practical AI workflows that help you get more customers and more views...
I send them to 38k readers every single week. Join here for free: https://t.co/w58ixO3TTf
When you leave an HFT, they put you on a non-compete for 1 or even 2 years! This is the biggest gift from HFTs to open source world.
Aman Gupta is being paid by Jump Trading (to sit at home) just added multi-token prediction to llama.cpp which speeds up local LLM models by 2x