Making things with AI. Sharing the process, the results, and the happy accidents🦊
Joined October 2026
- Tweets55
- Following25
- Followers34
- Likes237
Claude Code vs Blender is getting f*cking ridiculous
One approach builds a jet engine by hand
The other turns a written description into a programmable 3D scene with rotating turbines, mechanical components, realistic materials, and cinematic camera movement
And the difference goes way beyond modeling speed
Traditional Blender workflow:
> MODEL individual mechanical components
> POSITION and assemble the geometry
> CONFIGURE materials, lighting, and cameras
> ANIMATE every moving mechanism
> REWORK the scene when specifications change
Claude Code + Blender Python:
> GENERATE geometry from parameters
> ASSEMBLE components programmatically
> CONTROL turbine rotation through variables
> AUTOMATE lighting and camera movements
> REBUILD variations by editing the script
The interesting part isn't that AI magically replaces Blender
It's that Claude Code can operate Blender through Python, turning repetitive manual work into a reproducible system
Want to test the difference?
Open Claude Code and ask:
"Generate a Blender Python script for a detailed turbofan engine with separate compressor and turbine stages, parameterized blade counts, independent shaft rotation, metallic materials, and a cinematic camera orbit
Keep the geometry modular and expose the main parameters so I can regenerate variations without remodeling everything"
Blender remains the rendering engine
Claude Code changes how you build and control the scene
Bookmark this workflow before your next 3D project
truly don't understand why nobody is using this setup
graphify, a tool that turns any folder into a knowledge graph your agent can query, just passed 137k stars on github and got into Y Combinator. people stopped asking ai questions. they're giving it a desk, a memory and a job.
you give Claude Code one folder, plug in your email, calendar and a browser, and it turns into an agent. it reads, remembers, acts, and checks itself before it does anything stupid.
doesn't matter if you're a founder, a marketer or a student, you need this
the full setup:
> create a folder called AGENT, open Claude Code inside it and add a CLAUDE.md with one rule: "save every decision, person and project to memory/"
> run npm install -g @googleworkspace/cli, then gws auth setup. now it reads your Gmail, Calendar and Drive
> run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser to open sites, fill forms and pull data for you
> run uv tool install graphifyy, then graphify install, then type /graphify .. everything in the folder becomes a knowledge graph it queries in seconds instead of digging file by file
> run npm i -g jev-guard, jev-guard key "...", jev-guard install claude. a tiny model called Jev scores every action before it runs. rm -rf gets blocked, a poisoned email gets flagged, for about 5 cents per 1,250 checks
> type /schedule and tell it "every morning at 7:30, send me what came in, what you drafted and what waits for my yes". from now on it works on a routine
20 minutes to set up, and you never start from a blank chat again.
every repo is below:
- > github.com/googleworkspace/c…
-> github.com/microsoft/playwri…
->
github.com/Graphify-Labs/gra…
->
github.com/leepokai/jev-guar…
bookmark this
I JUST LAUNCHED 250 AI AGENTS WORKING SIMULTANEOUSLY. It’s not even about how fast they work, but the fact that they are physically incapable of misleading me
I spun up a real-time command center: 250 instances of Claude Fable 5.1 generating data in parallel, while Jev handles backend validation to cross-check every single output against its primary source. This goes way beyond standard acceleration. It’s a self-contained ecosystem that won't rest until every last discrepancy is wiped out
I set them loose on 80 IT companies
First pass: 18 issues flagged, broken APIs, fake metrics, empty endpoints
Second pass: narrowed down to 9 failures
Third pass: total clean-up, zero errors remaining
This isn’t just another agent flex. It’s a fully autonomous workflow that fixes its own mistakes before I even lift my laptop lid
If you know how to build systems like this, you’ll never have to worry about job security
If you don’t, the article linked below was created specifically for you
Perplexity Computer can now run fully local on your Mac.
Work with your native Mac apps and local files, and run tasks without sending sensitive data to the cloud. The model and the agent both run on your Mac.
Available now in the Perplexity Mac app.
HOLY SH*T my Grok AI agents woke up 8,640 times last month to find out nothing had changed.
one routine, running every 5 minutes. at $0.02 per run that's about $173/month.
run the same routine hourly and it's 720 runs, about $14.40.
same agent, same job, 12x cheaper.
so here's the 5-agent night shift i'd actually trust:
1. scout reads the feed and only reports what's new
2. quill drafts, but only from what scout flagged
3. critic kills any draft without a source
4. warden says no to anything risky
5. scribe files the survivors for the morning
then there's you. you're the 6th agent, and the only one who can hit publish.
the trick isn't making agents work harder. it's stopping them from waking up for nothing.
add a cheap "did anything change?" check before every full run. no change, nobody wakes up.
last night:
→ 195 ideas found
→ 117 dropped by critic and warden
→ 78 queued
→ 1 post i approved with my coffee
rule #1: a post at 3 a.m. stays a draft until you're awake.
the fox hunts all night. you pull the trigger.
full breakdown in the video ↓
TWO BROTHERS. $20K. A DOZEN AI TOOLS. $1.8 BILLION.
and no it's not a pitch deck, NYT literally checked his financials
Matthew Gallagher launched Medvi, a telehealth company selling weight-loss meds, in 2024. it took him 2 months and $20k to get off the ground. ChatGPT, Claude and Grok wrote the code, the site copy, the ads, even ran customer support
2025 → $401M in sales
2026 → tracking for $1.8B
team → him and his brother
for context Hims does similar money with 2,400+ people. Medvi's net margin is ~16%, Hims ~5.5%
but the real lesson isn't "AI replaced 2,400 people"
he didn't build doctors, pharmacies or shipping. he rented all of it. AI only runs the part the customer actually sees
own the customer, rent everything else. that's the whole playbook
and it's not pretty either lol. his support bot made up drug prices and he just honored them. once he pushed a tiny site update, went on a hike, checkout broke and he lost around 200 customers
his last company had 60 employees and never made a profit. this one has 2 and prints money
so is this the future of business or a house of cards waiting for one bad bug? 👇
21 smart wallets on Solana, selected from 110 traders. Combined PnL: +968 SOL.
QLO tracks new buys from selected wallets and sends alerts with the coin, purchase details and trader’s history. Autobuy can follow those purchases with the position size you set.
Here’s how these wallets made the list.
The scan started with 17 coins that passed $500K market cap in the last 48 hours. QLO pulled their top traders from DexScreener.
64 qualified for a closer look: they entered 5–20 minutes after launch, put in $40+ and took 3x+ on that coin.
Then QLO checked their wider trading history. 43 didn’t pass.
nobody is ready for this f*cking agent team
8 AI agents, 1 prompt, and a detective fox that runs the whole crew 24/7
it scouts the web, writes the code, reviews the PR, runs the tests, designs the screens, crunches the data, writes the copy and ships to prod while you sleep
one agent per step, from the first search to the final deploy
(1/8) Scout
finds facts and sources online
(2/8) Coder
turns a task brief into working code
(3/8) Reviewer
catches bugs before they ship
(4/8) Tester
runs the suite with no days off
(5/8) Designer
sketches screens and mockups
(6/8) Analyst
turns raw data into a report
(7/8) Writer
drafts posts, docs and release notes
(8/8) Shipper
deploys in one click and watches prod
the loop:
prompt → plan → code → check → ship
pick a task, click once, let the fox do the rest ↓
I made a concept for an AI crew that ships an app overnight.
Same job, two ways (illustrative numbers):
Human team: 3 weeks, $4,200
Night Crew: 11 minutes, $3.40
most AI builds die the same way: you give one agent the whole messy job and it drowns in context
Night Crew splits the job instead
Captain writes the plan, then sits idle the whole run, so you pay almost nothing for it
Scout reads 212 pages once and writes a spec: audience, must-haves, pricing, risks
8 Builders take one slice each (landing, brand, copy, API, payments, emails, SEO, analytics), and none of them touches the raw research
Checker merges everything and runs 64 checks. 64 of 64 pass
Captain plans. Scout researches. Builders ship.
concept video, built with code, with a fox 🦊
Useful topic. One practical note for anyone following along: the REA README warns about lookalike repos, so install only from the official github.com/morluto/rea, and only use it on software you're allowed to analyse.
HE WASN'T LOOKING FOR HIS CAR
She was leaning on his Audi
Denim skirt riding up just enough
Braids with colorful clips like she planned every detail
He walked up from behind
Hands in his pockets
Eyes going where they shouldn't
She felt him before she saw him
Crossed her legs slower than she needed to
And smiled like she already knew
He stopped. She didn't move.
The skirt shifted again
And suddenly the parking lot felt smaller
Underground. No cameras. No witnesses.
Just her laugh bouncing off the concrete
And a boy who forgot his own name
Warren Buffett has lived in the same $31,500 house since 1958. Then a shareholder asked him: real estate or stocks?
His answer at the 2025 Berkshire meeting: there’s just so much more opportunity in stocks.
A stock trade is done in seconds. In real estate, he said, signing the deal is just the beginning. Then the negotiating starts again.
Even Charlie Munger’s real estate deals were, in Buffett’s words, little more than a hobby.
The numbers back him up. Since 1988, US home prices are up 374%.
The S&P 500 with dividends is up over 5,000%.
$10,000 in a house became about $47,000. In the index, about $510,000.
Your house or your portfolio, which one is really making you rich?
THIS IS THE WORLD RECORD NOBODY TALKS ABOUT
Forget speedrunning. Forget Rubik’s cubes. The real competition in math is building shapes with the most holes.
A polyhedron made entirely of regular polygon faces. No cheating. No curved surfaces. Just triangles, squares, pentagons locked together. With 291 tunnels running through it.
The shape is called “Squilliams.” It broke a record that has been traded back and forth between obsessed geometers since the 1970s.
The previous record was 87. Someone nearly tripled it. And mathematically there could be shapes with thousands of holes. Nobody has found the ceiling.
How is this not the most addictive math competition on earth?
February 28, 2006. Anna Nicole Smith walked into the US Supreme Court to fight for a share of a $1.6 billion oil fortune.
She had married J. Howard Marshall when she was 26 and he was 89. He died 13 months later and left her nothing in his will.
Dozens of cameras followed her up the steps.
Two months later the justices ruled for her, 9 to 0.
She never got to use the win. She died in February 2007 at 39.
Her estate went back to the same court in 2011. This time it lost, 5 to 4.
Two Supreme Court cases. Not one dollar from his estate.
Did she deserve a cut of his fortune?
I TURNED THE TESLA ROADSTER STUNT INTO A MOVING SKETCH — 15 SECONDS, 922 FRAMES, ONE WILD FLIGHT
a car flying over a row of vehicles already looks unreal — give it the look of a moving concept drawing and it becomes something else entirely
thin black lines, a red outline, an almost empty page
then the Roadster starts moving
upside down → over the row → wide angle → mid-air flip → touchdown
the idea was to make the whole sequence feel like a page from a designer’s notebook suddenly started playing
the ramp stays visible. the parked cars give the jump scale. the red tracking marks keep your eyes on the Roadster as it rotates through the air
you can follow the stunt through just a handful of lines
and that is my favorite part of this look: every outline has something to do
the roofline shows the rotation. the ramp shows the height. the cars underneath make the gap feel bigger. then the landing dust spreads across the sketch
there is a moment in the wide shot where the whole thing looks like someone drew an impossible idea on paper
a few seconds later, that idea has already flown across the page
the red accents carry through the entire edit — around the car, beneath the captions, into the final title
UPSIDE DOWN.
OVER THE ROW.
MID-AIR FLIP.
TOUCHDOWN.
each caption gives the next movement its own beat
then the motion clears and the final ROADSTER card fills the screen, like the closing page of an animated concept presentation
922 frames in a 1080p fan edit — a flying car, a sketchbook aesthetic, and a landing that disappears into dust
watch the red outline during the flip. that is the moment I would replay
which car should get the sketch treatment next? ↓
