Andrej Karpathy spent 2h showing how he actually uses AI day to day
he's a co-founder of OpenAI and led AI at Tesla, so when he shows how he works, it’s worth watching
and the whole session is just him telling the machine what he wants in simple terms, like he's briefing a coworker
watch what's actually happening the entire time:
> he describes the task in normal words
> it goes off and does the work
> he glances at the result and nudges it with one more sentence
that's the whole skill, and you've had it since you learned to talk
the only gap between that and a worker that runs on its own is handing that sentence a schedule and the tools to act
check his work, then build the version that keeps working when you stop
Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
this is one of the best workflows I've seen in a long time
in this video she breaks down exactly how most people are using Claude:
- the 14% you lose to CLAUDE.md before typing a word
- the plugins that 95% of users have never installed
- the workflows that run without you typing a single prompt
- why typing one prompt and closing the tab is leaving 90% on the table
if you've been using Claude for months and still start every session from scratch, you have at least 28 untouched features. probably 30
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
How to duplicate yourself into Claude in a weekend:
(even if you've never written a prompt before)
1. Download the desktop app.
☑ Go to claude .com/download
☑ Set Opus 4.7 as default
☑ Turn ON Extended Thinking
2. Open Cowork mode.
☑ Cowork = where your voice lives
☑ Click the top left tab
☑ Create your "Voice" folder inside
3. Install Wispr Flow (it's free).
☑ Turns your voice → text
☑ Voice = faster and more honest
☑ Typing kills the truth.
4. Run the interview.
☑ Paste Prompt 1 from https://t.co/LyV7feh2TK.
☑ 100 questions, 7 categories
☑ Push past every vague answer
5. Compress the dump.
☑ Paste prompt 2 from https://t.co/LyV7feh2TK.
☑ 20K words → 4K tokens
☑ Save as [your_name] .md
6. Test it in a blank chat.
☑ Open a fresh Claude chat
☑ Run a prompt only you would write
☑ If it sounds like you → ship it
7. Drop it into Cowork.
☑ Move [your_name] .md into your folder
☑ Claude now reads it on every turn
☑ Every draft = your voice, automatically
8. Port it everywhere.
☑ Upload to ChatGPT, Grok, Gemini
☑ Same file = same voice in every AI
☑ Hand it to your team or ghostwriter
9. Edit it forever.
☑ Install Obsidian (free)
☑ Open Cowork as a vault
☑ Update as your taste shifts
Full guide + prompts at https://t.co/LyV7feh2TK.
(save this to clone yourself into any AI)
Anthropic CEO: "AI will write 100% of code within a year"
developers spend 4 years in university learning to code
Claude learned it from every book ever written
if the hardest skill is already handled - the gap is no longer about what you know
it's about how well you've configured the tool that knows everything
most people haven't done that yet
the article below is where you start
The person who built Claude Code just showed exactly how to use it.
30 minutes. Free. Straight from Boris Cherny himself.
Bookmark this before you forget.
Most people using Claude daily are missing 40+ features hiding in plain sight.
This single session is worth more than any $1000 course.
🚨 Claude can now build Goldman Sachs–level financial models for free.
I’ve put together 12 prompts that can literally replace $150K/year investment banking work:
3. One-Number Weekly Check-In
"Give me the single most important number I should track every Sunday to know whether I'm moving toward wealth or away from it. Then build a dead-simple 5-line weekly dashboard around it."
🚨 BREAKING: Claude can now build your entire personal budget and destroy debt faster than $3,000 financial advisors. For free.
Here are 12 prompts that take you from financial chaos to total control in 30 days:
(Save this before it disappears)
L’équipe d’Anthropic vient de montrer comment vraiment prompter Claude.
24 minutes. Gratuit. Par ceux qui l’ont créé.
Regarde le workshop. Ajoute en signet 🔖
Ça vaut plus que tous les cours à 300 $ que tu as failli acheter.
Instead of watching an hour of Netflix, watch this 2 hour hour Stanford lecture will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.
Instead of watching an hour of Netflix, watch this 2-hour Stanford lecture on AI careers. It will teach you more about winning in the AI race than all the AI content you’ve scrolled past this year.
BREAKING: I asked Claude to upgrade my LinkedIn profile.
It didn’t just “upgrade” it. It turned it into a recruiter magnet.
Here are the exact 15 prompts I used:
Most people are still prompting AI.
The top builders are designing agent systems.
This document quietly maps 21 real agent design patterns — from prompt chaining → multi-agent systems → memory → MCP → RAG → guardrails → evaluation.
If you're building with AI and not using these, you're already behind.
Here’s the cheat sheet:
• Prompt Chaining — break tasks into reliable steps
• Routing — send tasks to the right model/tool
• Parallelization — run agents simultaneously for speed
• Reflection — agents critique and improve outputs
• Tool Use — agents call APIs, DBs, code
• Planning — long-horizon task execution
• Multi-Agent — teams of specialized agents
Then it goes deeper:
• Memory Management — persistent context
• Learning & Adaptation — agents that improve
• Model Context Protocol (MCP) — tool standardization
• Goal Monitoring — agents track progress
• Human-in-the-Loop — controlled autonomy
• RAG — grounded knowledge retrieval
And the advanced layer most people miss:
• Inter-Agent Communication (A2A)
• Resource-Aware Optimization
• Reasoning Techniques
• Guardrails / Safety Patterns
• Evaluation & Monitoring
• Prioritization
• Exploration & Discovery
This is basically a blueprint for production-grade AI agents.
Not theory.
Actual architecture patterns used by serious teams.
Bookmark this.
Study one pattern per day.
You’ll be ahead of 95% of AI builders in a week.
Doc link ↓
https://t.co/9ppSWHXHyp
This guy left a $400K job at @Meta...
to build something most people don’t understand yet.
Not because he had to.
Because he saw what’s coming.
For months, he was doing what we all do:
Slack, follow-ups, tracking work.
Then it hit him:
“Why am I doing work software should already handle?”
So he built an AI employee.
Added it to Slack… and it started working:
• finds customers
• follows up
• flags issues early
No prompts.
That’s the shift:
AI isn’t executing anymore.
It’s deciding.
He left — and built this:
https://t.co/EO0vccfFLV