Angehefteter Tweet
Hex Horizon
113 posts
Hex Horizon
@Noderunner_Hex
software developer / innovation builder / venture contributor
404: not found Beigetreten Haziran 2026
113 Folgt53 Follower
My gf makes $400k / year selling books she never writes
I found out last night, and we dated for 3 years
back then she used to type them out herself on her laptop, $21 a book
now she hands ChatGPT a topic and a page count and gets 90 pages back
Claude designs the cover, she uploads it and it sells for $21
reading one of her books takes longer than making one
she's shipped 27 so far, each one an afternoon of work
then it just sells, every single day
she started 10 months ago with a single prompt
that's the whole idea behind the 35 Claude workflows I put together, set it up once and let it run while you sleep
Avid@Av1dlive
English
@ardchain $65k is right enough to pay the bills and live the best life
good one
English
THIS OPERATOR BUILT A MASTER DASHBOARD TO AUTOMATE HIS $65K/MONTH AGENCY
Here is the exact architecture of his visual operating system:
- A unified content pipeline for all social platforms.
- Live Facebook ad tracking mapped directly to sales.
- Automated SMS & Email follow-up triggers.
- Centralized finance and customer admin.
Instead of switching between 10 different apps and losing context, every department is integrated into a single bird's-eye view.
The ultimate flex isn't just the revenue. It's having zero operations living inside his head, allowing him to scale with absolute clarity.
Ridark@ridark_eth
English
A 9-year-old built a real online store in 10 minutes.
No code. No engineers. No budget. She just told an AI agent what she wanted.
Her dad runs AI for BNP Paribas, a 180,000-person bank, and he didn't tell it as a cute story.
"My nine-year-old became a new node in this new agentic ecosystem that is the economy."
The work was never the bottleneck. Intent is. And no one runs half a million agents by hand, so they run in loops that govern each other.
Watch it, then read how to build the loops behind it, below.
Phosphen@phosphenq
English
this repo probably should not be free
it teaches you how AI builders are replacing prompts with autonomous loops
while everyone is trying to write the perfect prompt
they're building systems that:
discover -> plan -> execute -> verify -> improve
over and over again
inside you will find
> production ready loop patterns
> memory & evaluation frameworks
> tool calling workflows
> self correcting agent templates
> human in the loop safeguards
> starter projects you can run today
this is the shift from asking AI to building AI that asks itself
bookmark this before everyone catches on
repo link - github.com/cobusgreyling/…
MIKE@mikenevermiss
this is f*cking dangerous someone just open sourced the entire "LOOP ENGINEERING" framework for free the guy who built Claude Code at Anthropic said it himself: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops. stop prompting your agent. build the thing that prompts it for you. discover → plan → execute → verify → repeat you used to be inside that loop loop engineering is you stepping out of it entirely the repo includes: - 6 production ready patterns (daily triage, CI sweeper, PR babysitter) - clone and run starters for Claude Code, Codex, and Grok - a loop readiness CLI that scores your codebase - SKILL. md templates, STATE.md spine, full safety docs use this one command to start(copy/paste): npx @cobusgreyling/loop-init • --pattern daily-triage -tool claude-code bookmark before this blows up repo link : github.com/cobusgreyling/…
English
ONE GUY TURNED 2 OBSIDIAN FOLDERS INTO A SECOND BRAIN THAT TALKS BACK
CarrotProximity, FoxProximity, HungerLevel, ThreatLevel. The thing decides when a rabbit flees.
That's the joke.
People are watching a prey animal make survival decisions and realizing their notes app can do the same thing.
The setup is two folders inside Obsidian. One holds raw notes. The other holds the index the model queries against.
That's the entire architecture everyone is paying 30 dollars a month for in some SaaS wrapper.
A second brain is not magic. It is weighted connections between inputs you already wrote down.
The rabbit does not think. It pattern matches against threat and proximity.
Your notes do the same when you stop treating them like a graveyard.
The people who figured this out 6 months ago are now charging 2k per setup to consultants who still email PDFs to themselves.
The tools have been free for a year.
The bottleneck was never the model.
It was whether you actually wrote anything worth indexing.
chewa@chewadot
English
CLAUDE CODE + OBSIDIAN IN UNDER 1 MINUTE
The trick is not “AI note taking.”
It is giving Claude Code a place where your thinking already has structure.
The video’s setup is simple:
download Obsidian,
put your notes in one vault,
keep them as local .md files,
then connect that vault to Claude Code through the Obsidian CLI.
Now your notes stop being a pile of old thoughts.
They become files Claude can read like a codebase.
Project notes can connect to meeting notes.
Ideas can connect to goals.
Open loops can connect to old decisions.
Then the useful part starts: custom commands.
A /today command can pull calendar context, tasks, recent notes, and active projects into one prioritized plan for the day.
An /emerge command can scan across months of notes and surface the ideas you keep circling but never clearly named.
That is the actual workflow:
Obsidian stores the thinking.
Claude Code operates on the thinking.
Commands turn it into repeatable output.
The caveat is obvious but important:
this only works if the vault has signal.
Random clipped articles, messy dumps, and half-written fragments will produce messy answers.
But if your vault has meetings, decisions, goals, tasks, project context, and recurring problems, Claude Code gets much more useful.
Stop asking it isolated questions in a blank chat.
Give it your thinking substrate.
Then make it run commands on top of it.
kocer@kocer_eth
English
THIS GUY IS USING WI-FI TO DETECT PEOPLE THROUGH WALLS.
No cameras.
No sensors.
Just tiny changes in Wi-Fi signals.
It can detect movement.
Human presence.
Even breathing.
Five years ago this would’ve sounded like science fiction.
Today it’s a weekend project.
The crazy part?
You could build a simple demo around this idea and put it online for $0.
That’s exactly why I wrote a guide showing how to launch a real website with a custom domain - completely free.
Full setup below
kiosa@thegreatest_sv
English
Creator of Claude Code, Boris Cherny:
"While you're prompting your agent step by step, mine writes itself, reviews itself, and picks its own next task."
In 26 minutes he and Spotify Chief Architect reveal how AI already runs their entire codebase, and what comes after.
Watch it, then save the step-by-step guide below 👇
rody@0x_rody
English
3TB HOME AI RIG IS RUNNING MODELS PEOPLE STILL PAY OPENAI TO ACCESS
Same box runs DeepSeek 671B, Kimi K2 at one trillion parameters, and five models loaded at once without choking.
This is roughly $25k-30k in hardware doing work that costs $2k-5k a month in API calls or cloud GPU rentals, depending on usage.
The real shift is Apple quietly turning unified memory into the cheapest path to local inference.
No NVIDIA tax, no H100 waitlist, no data leaving the room.
Frontier models stopped being a moat the moment a guy in his office could run them off a power strip.
The cloud AI business was priced assuming individuals couldn't host this.
That assumption is now wrong by a factor of ten.
Compute is decentralizing faster than the pricing models can adjust.
NO1ennn@N01ennn
English
THIS GUY BUILT A COMFYUI WORKFLOW THAT TURNS ONE AI GIRL INTO A CONTENT PRODUCT
The video is not just “make a pretty AI girl.”
It shows the real money part:
repeatability.
ComfyUI lets you lock the character, load the model stack, use a reference image, batch prompts, and generate many shots with the same face, style, and vibe.
That is the difference between random AI art and an asset you can sell around.
The simple path:
Pick a niche first.
Fitness girl, fashion girl, gaming girl, luxury travel girl, skincare girl, anime-inspired creator.
Then build a consistent face and visual style in ComfyUI.
Not 1 image.
A bank of 100+ usable posts.
Then monetize the output in one of 4 ways:
1. Sell content packs to small brands that need ad creatives.
2. Build a synthetic influencer page and test affiliate offers.
3. Create custom AI model/look packages for creators who want a character but do not want to learn nodes.
4. Sell the workflow, prompts, and setup as a productized service.
The mistake is thinking the model is the business.
The business is the boring system around it:
consistent character, content calendar, offer, distribution, and proof that the visuals convert.
ComfyUI gives more control than simple AI image apps because the workflow can be repeated, edited, and improved instead of praying for one lucky generation.
But the caveat is big:
an AI girl with no niche, no offer, and no audience is just another folder of renders.
If you want to make money from this, do not start by generating “hot girl” images.
Start by asking:
who pays for this visual attention?
what product can she sell?
what content can be posted every day?
what makes the character recognizable after 3 seconds?
That is where the money is.
Lummox@Lummox_eth
English
A $40 BC250 BOARD WITH 16GB GDDR6 GETS A GITHUB FIRMWARE FLASH, THE DEFAULT 8/8 CPU/GPU SPLIT REWRITES TO 0.5/15.5 AND OPENS 15.5GB OF UNIFIED MEMORY TO OLLAMA, DEAD CRYPTO HARDWARE JUST DOUBLED ITS AI CEILING
01:08 the operator points at the chart, "you only give 512 megs to the GPU part and that's reserved, that means all the rest of the RAM is available to either the CPU or the GPU"
a BC250 ships from the factory with 16GB GDDR6 split 8/8 between Oberon CPU cores and the RDNA 2 iGPU, the iGPU only ever uses 4-5GB during inference, the other 3-4GB sits stranded
SEC Bolt's firmware mod on the moth-enjoyer GitHub flashes a 0.5/15.5 split, the GPU reserves 512MB and 15.5GB falls into a unified pool that ollama treats as VRAM, qwen 3.6 14B at 4 bit fits with 2GB context headroom
15.5GB on a $40 board with a $40 CH347 flasher beats the $249 Jetson Orin Nano's 8GB by nearly 2x at 1/6th the price, the firmware is open source, the dump backup process takes 4 minutes per board
your map's tier zero floor was the OptiPlex at $35-50 with iGPU only, the modded BC250 sits at the same $40 mark with 15.5GB of GDDR6 and an actual RDNA 2 GPU, the buyer who flashes once unlocks a 13B class local AI host for the price of a dinner
the window is open, follow and bookmark before it closes
starmex@starmexxx
English
🚨THIS UPDATE KILLED CLAUDE
GLM-5.2 by @Zai_org hits the same ~74% score as Opus 4.8
While burning HALF the tokens...
Same brains, half the bill.
Why would you ever pay frontier prices again?
Full research attached below.
Hex Horizon@Noderunner_Hex
English
@51bodila when you say it this way, it just feels different
but I agree mostly here anyway
English
Fidelity Vice Chairman told a room of investors: "if you can't explain to a 10-year-old why you own a stock - you shouldn't own it " - then gave them the system he used to turn $18 million into $14 billion
"I skipped every tech stock on Wall Street - bought Dunkin' Donuts - made 10 times my money - because I could understand donuts "
he averaged 29.2% a year for 13 years and no one has beaten that record, then retired at 46 - this is how he thinks for free
"a fireman put $2,000 a year into one stock, no computer, no MBA - just an observant neighbor - became a millionaire "
Warren Buffett called his house and asked to use his quote
$1,000 invested with him turned into $28,000 - one out of every 100 Americans trusted him with their money
bookmark & watch today ↓
bodila@51bodila
Goldman Sachs Vice Chairman told students: "most of you won't succeed" - then gave them the exact 18 rules he used to become the person Fortune 500 CEOs call first "give your client advice that is against your own interest - that's the fastest way to earn trust - most bankers will never do this " Goldman Sachs MDs make $1-3 million a year - this is exactly how they do it - in 23 minutes for free "don't take no for an answer - from getting reservations at a restaurant to getting a billion-dollar client - never ever ever ever ever give up " he said 15-min a day reading the Wall Street Journal will make you smarter than 90% of Wall Street within 6 months - no one does it bookmark & watch today ↓
English
ONE GUY MAPPED AN ENTIRE CITY'S ECONOMY INTO A 3D PARTICLE SIM IN 7 DAYS
He took Bozeman's economic data and turned it into a spherical point cloud you can fly through.
Zoom in, zoom out, render it as volumetric smoke, watch the motion trails in yellow and blue.
One week. One monitor.
One person narrating it like it's a weekend project.
This is what Karpathy was pointing at. The bottleneck was never the data. It was the interface. Spreadsheets and dashboards compress 4D information into flat rows because that's all the tools allowed.
Now a solo operator runs Houdini-grade simulations on a consumer GPU and treats regional GDP like a VFX shot.
That used to be a 6-person studio quoting 80k for a 30-second render.
Every "second brain" app from the last 5 years is still text in boxes. Notion, Obsidian, Roam. Linear notes about non-linear systems.
Meanwhile this guy is flying a camera through the actual shape of a local economy.
The note-taking era peaked.
Spatial data is the next default.
0xMarioNawfal@RoundtableSpace
Google Flow now has access to Google Maps Street View. Activate the Agent Mode and prompt it to create an image based on an address in the US. Google Flow will recreate the image, and then you can decide how to animate it.
English
🚨THE LOOP IS NOW INSIDE THE MODEL
GLM-5.2 by @Zai_org doesn't stack 100 layers.
It runs ONE block again and again.
A loop, baked into the wiring.
A small model thinking in circles to punch like a giant.
Same trick the whole frontier quietly runs on.
Full research below.
Hex Horizon@Noderunner_Hex
English
@starmexxx being a software engineer is now 100x cheaper than a year ago
English
ONE BUILDER LINED UP A $130 N97 MINI PC WITH 16GB RAM, AN AMD BC 250 PACK OF 12 AND A $599 MAC MINI AND SAID YOU CAN RUN AI ON LITERALLY ANY OF THESE, A WHOLE BUDGET STRATA UNDER YOUR JETSON ENTRY POINT
02:10 the operator picks up the mac mini and says, "you can actually run ai on literally any of these"
he walked through a $15 raspberry pi zero 2w, several pi 4 builds, an odroid, a thin client, then an n97 mini pc with 16gb of ram and a 512gb ssd that costs about $130 right now
the amd bc 250 on the desk next to it is an entire mid-range gaming computer on a card that ships 12 to a box for around $300 total, the same chip that drove ethereum mining now sells used to local ai builders
your map starts at the $249 jetson but the n97 box sits below it, $130 for 16gb of ram and a quad-core chip is enough to run ollama with mistral 7b at usable speed for daily ai tasks
the $5,500 a year a heavy claude code and chatgpt pro user pays kills itself in 4 weeks on a $130 box, every month after that is loose change in electricity for the same daily ai work
bookmark this and read the article below
starmex@starmexxx
English
Data center compute costs $30,000/year to run the kind of self-improving AI agent that now fits on a desktop with an RTX 3090!
Hermes Agent writes its own skills from experience. Completes a complex task, saves the procedure as a skill file on disk, and the next time it needs to do something similar, it opens its own skill and improves it rather than starting over.
Independent benchmarks show agents with twenty or more self-created skills complete similar future tasks 40% faster than fresh instances.
Three-layer memory running underneath. Persistent notes for preferences and project conventions. Searchable session history. Procedural skills holding the actual learned workflows.
After a month of use, your Hermes is genuinely different from anyone else's. It knows your codebase, your conventions, and how you like things explained.
30 minutes to set up. Complete guide with exact commands for LM Studio and Ollama.
Bookmark so you do not lose it!
Follow @neil_xbt for more Hermes Agent content!
NeilXbt@neil_xbt
English
Hex Horizon retweetet
AN 18-YEAR-OLD JUST SOLD AN AI-INFLUENCER SYSTEM FOR $120,000
Not a product. Not a course. Infrastructure.
The kid in the hoodie already cashed in on it.
He built automated AI influencers, packaged the workflow, and sold the entire backend to an agency that didn't want to build it themselves.
$120k for what is essentially a few connected APIs, a content pipeline, and a face that doesn't exist.
Agencies used to buy media. Then they bought creators. Now they buy the machine that replaces the creators.
The interesting part isn't the $120k
It's that an 18-year-old understood faster than the agency that the bottleneck moved from talent to systems.
They paid him because building it in-house would cost more in time than in cash.
UGC at scale used to mean 50 creators and a coordinator. Now it means one teenager with a server.
The arbitrage window between people who build this and people who still hire for it is the whole business right now.
Ridark@ridark_eth
English
@slash1sol imagine those people simply predict the future and know exactly what tech updates are coming soon
English
IN 2011 RICH HICKEY CALMLY EXPLAINED WHY ALMOST EVERY CODEBASE ON EARTH ROTS INTO AN UNFIXABLE MESS. THE CAUSE WASN'T BAD PROGRAMMERS -- IT WAS ONE WORD EVERYONE USES WRONG EVERY DAY.
61 minutes from the creator of Clojure, in one of the most quoted talks in software.
-> The idea that lands: you keep confusing "Simple" with "Easy". Easy means familiar and close at hand. Simple means not tangled together. They are not the same thing.
Easy stuff feels fast today, so you reach for it and quietly braid everything together until nothing can move.
Simple is harder up front, but it is the only thing that stays cheap to change later.
Fourteen years later this is the whole AI-coding trap: the model ships "Easy" code in seconds, tangled and fast, and the complexity bill comes due anyway.
Speed was never the real skill -- keeping things untangled so you can still change them is. This is where you learn the difference.
Most people chase whatever is easy. The ones who watch this build things that survive.
Save this. Watch it tonight. ↓
slash1s@slash1sol
IN 2010 AN MIT LEGEND SHOWED THAT MOST OF MACHINE LEARNING IS JUST MEASURING HOW CLOSE TWO THINGS ARE 49 minutes from Patrick Winston, who taught MIT to think about thinking for decades. -> The idea that lands: a machine does not "Recognize" anything. It measures how close you are to examples it already has, and picks the nearest one. No understanding, no intuition. Just distance -- how far is this new thing from the stuff it has already seen. Winston builds the whole method from scratch on a chalkboard, and the magic quietly disappears. That simple trick is everywhere now -- face unlock, recommendations, search, the retrieval behind half the AI products you touch. Modern models turn everything into points in space and grab the nearest neighbor. This is that idea, before it scaled. Chasing the buzzwords was never the skill -- seeing the simple measurement underneath is. This is where you learn it. Most people think AI recognition is some black box. The ones who watch this know it is mostly a ruler. Bookmark it. This one's a legend. ↓
English