made with seedance + chatgpt
(prompts below)
Meet Victor Bodega
Dominican bodega owner on one of the roughest blocks in NYC
Every night after closing, trouble finds him
Too bad for them, the keys don’t just open doors
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 he 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 caching setup that keeps it at 95% hit rate and almost free
- why starting every chat from zero is the slowest way to use Claude
if you've been using Claude for more than a month and never left the chat window, you've been using one project when you could be running a team of them
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
Andrej Karpathy:
"90% of what AI Twitter tells you to learn will be dead in 6 months."
He's right.
The dead list is already obvious:
AutoGen. CrewAI. Autonomous agent pitches. Agent marketplaces. Benchmark leaderboards. Horizontal "build any agent" platforms.
Demos that break in production.
Hype that goes viral on Monday and vanishes by spring.
Frameworks that senior engineers stopped chasing months ago.
What actually compounds:
Context engineering.
Tool design.
Orchestrator-subagent pattern.
Eval discipline.
The harness mindset — harness beats model, always.
MCP as the protocol layer.
The edge isn't the newest framework.
It's understanding the basic concepts that survive every framework cycle.
Before you write a single line of code — read this ↓
I spent a week finding the 10 Obsidian plugins that actually matter.
There are 2,700+ in the community store. These are the only ones you need.
Here are the Top 10 Obsidian GitHub repos worth bookmarking:
1. Dataview
https://t.co/cx7Vja0rY2
Query your entire vault like a database. Build dashboards, indexes, and dynamic lists from your notes metadata.
2. Templater
https://t.co/qHAC7R974l
Far more powerful than core templates. Dynamic variables, JavaScript execution, and automated note creation.
3. Excalidraw
https://t.co/clMeUNx4oT
Full drawing and diagramming tool inside Obsidian. Mind maps, wireframes, and sketchnotes linked to your notes.
4. Tasks
https://t.co/EIyYDWUazi
Track tasks across your entire vault with due dates, priorities, recurrence, and powerful filters.
5. Obsidian Git
https://t.co/wdxQi7MfaE
Version control and automatic backup using GitHub, GitLab, or any Git service.
6. QuickAdd
https://t.co/Tq9eGdwLDw
Capture ideas and create notes in the right folder with one keystroke. Fastest way to add content to your vault.
7. Kanban
https://t.co/EzDKZ5GOnf
Markdown-backed Kanban boards inside Obsidian. Your project management lives with your notes.
8. Smart Connections
https://t.co/dtYrd4yLMa
AI-powered note connections. Finds semantically similar notes and lets you chat with your vault.
9. Calendar
https://t.co/QEgs3TQ9G7
Simple calendar widget that integrates with your daily notes. Navigate your vault by date.
10. Linter
https://t.co/80SjI67pFM
Auto-formats notes on save. Consistent styling, frontmatter structure, and clean markdown across your entire vault.
All free. All open source. All actively maintained in 2026.
CLAUDE DESIGN FULL 1 HOUR COURSE
❤️🔥Just Recorded a Full Course on How To Build Interactive Animated Website with AI.
Bookmark this before you forget.
The hardest part of building a good skill or Claude Code OS is getting your knowledge out of your head and into the system.
So use this skill.
Give this a 2 min read.
Alex Hormozi explains what to do when your ads stop working.
"Facebook probably starts by focusing on people who know who you are. And if you have a tiny little pool of people, then it'll quickly go through those people. You'll make your sales and then it'll go to one degree removed. And when it goes to one degree removed, those people don't know you at all, and they're less likely to convert."
"The people I'm seeing consistently outperform are the people who have two communities. They have the free community because it's very easy to convert people into free communities. If you can get 20% or more to opt into the community, that's a good normal benchmark to shoot for. If you manually work the leads, you can get about 10% of those people to buy the next thing."
Jane Street needed a 4,032 GPU liquid-cooled data center just to run their trading models
> that tells you everything about how much money this firm makes
and why their quants start at $400K/year
someone just got inside and filmed it
> custom AI and trading agents trained specifically for this firm - off-the-shelf doesn't cut it
> packets processed in under 100 nanoseconds
> copper over fiber because electrons beat light at that scale
> automated kill switches to shut algorithms down before downtime costs millions
> financial privacy of their positions is protected at infrastructure level - nothing leaks
20 years ago their cluster was 6 Dell boxes on an office floor
> this is the machine now
what do you think - is this level of infrastructure even possible for smaller firms?
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, then mapped everything he described to what Claude can actually do today.
17 Claude features most people will never find on their own.
Full breakdown in the post below.
OBSIDIAN PLUS HERMES AGENT IS THE MOST POWERFUL PERSONAL OPERATING SYSTEM AVAILABLE RIGHT NOW AND ALMOST NOBODY HAS BUILT IT YET.
Obsidian holds everything you know permanently.
Hermes reads it, reasons across it, and runs your most important workflows automatically.
Morning briefs generated from your actual vault. Inbox processed every evening without you touching it. Project health monitored every Monday.
Weekly synthesis ready every Sunday.
One system. Thinks. Remembers. Runs your life.
Read this and Bookmark it now.
Life after realising Kimi Agent Swarm is completely free with unlimited usage and real-time web search across more than 1,000 websites
Kimi Agent Swarm + Claude Opus 4.8 = 300 agents gathering the data simultaneously and a 1M token context window reasoning across all of it in one session.
Kimi finds what matters. Claude decides what it means. Neither can fully do what the other does.
The full workflow with exact prompts is in the article.
A guy runs AI ads for local roofers and they pay him $2,000-$5,000 a month each
he doesn't film anything. He doesn't hire anyone
he opens Facebook's Ad Library and finds ads that have been running for 6+ months - those are the proven winners
then he drops them into Higgsfield and has it rebuild the same ad with the client's logo
claude writes the script and the ad copy for him
in one afternoon he's got 10-15 video ads for a roofing company that never ran a single ad before
he launches them on Meta and leads start coming in through a simple form
an AI bot texts every lead back in under 2 minutes and books them straight onto the client's calendar
the roofer just wakes up to booked appointments. He has no idea AI did all of it
some of these clients have paid him the same fee every month for 2 years straight
he bills per lead or a flat retainer - either way it's recurring, and the AI does most of the work
one skill, a few tools, and small local businesses that have never touched advertising
save this, the quietest AI money right now isn't apps - it's running ads nobody knows are AI
INSTEAD OF opening Obsidian just to dump more notes tonight.
Spend 30 minutes studying these workflows.
12,900+ GitHub stars in under three months. Free.
The ones who connect plugins, workflows, and Claude will turn their vault into working memory.
Someone has dropped this Automated Polymarket bot with 4 layer risk protection with professional-grade risk management baked in.
> 4-layer protection - daily, monthly, drawdown, and total loss halt at 40%
> Smart Money Filtering only follows traders with 60%+ win rate and consistency checks
> Dynamic position sizing automatically scales down during losses, up during wins
> Whale detection prevents you from copying lucky one-hit wonders
Fully open source. Runs itself. Stops itself before it blows up your account.
THE RISK MANAGEMENT LAYER MOST TRADERS NEVER BOTHER TO USE.
Github: https://t.co/EuXJWMwdSa
A DEVELOPER TAUGHT GIT WITH A BOX OF CHILDREN'S TOYS AND ENGINEERS WITH TEN YEARS IN SAY IT'S THE FIRST TIME THE THING EVER ACTUALLY MADE SENSE
90 minutes, one table, a pile of Tinkertoys. No wall of jargon -- he builds a real Git repo out of plastic rods right in front of you.
-> The moment he snaps the first pieces together, Git stops being scary command-line magic and becomes what it really is: a chain of tiny objects pointing at each other.
Branches, merges, rebase, the staging area -- every concept that's ever burned you at 2am -- he rebuilds with toys until a four year old could follow. He calls Git a two-trick pony. After this you'll see exactly why.
Memorizing commands was never the skill -> holding the graph in your head is. And with an AI agent now committing and rebasing on your machine all day, that mental model is the only thing between you and a history you can't read.
Scroll the comments and you'll see the same thing over and over: this is the talk that finally made Git click and made people the one their whole team comes to when it breaks.
Bookmark & watch it today. It's the 1.5 hours that pays you back for the rest of your career ↓