Architect Photographer,Play with Synthesizers,Crypto enthusiast,Ai, machine learning, learning spatial computing engineering
Santa Clara, CA
Joined May 2012
- Tweets8.9K
- Following2.2K
- Followers261
- Likes10.6K
Erwin retweeted
Ok, this guy just LEAKED the EASIEST method to make money in 2026
Claude Code + YouTube = $62,000/month
Nothing complicated (just 13 minutes). Ready for you to replicate from home.
🔖 Save it, you won't see it again.
una chica de 17 años factura 7.800$ a la semana.
solo con Google Maps + Claude.
no ha hecho una web en su vida.
me reí. me enseñó su stripe. me quedé callado.
lo único que hace:
→ abre google maps
→ busca "tacos filadelfia"
→ elige uno de 4,7 estrellas
→ con web de 2013
→ copia sus datos
→ los pega en un constructor
→ sitio listo en 20 min
hace 6 meses ganaba 9$/h en mcdonald's. el uniforme todavía cuelga en su armario
envía la web terminada, con el nombre del negocio ya puesto, y se va a dormir
el dueño de la taquería abre el link. se lo enseña a su hija. "¿esto somos nosotros?" paga 4.800$ esa misma noche.
"¿esto va en serio? ¿cuánto cobras?" así fue su martes.
mes 1: 800$
mes 2: 4.100$
la semana pasada: 10.400$
una agencia web pediría 14.500$, cuatro personas y seis semanas.
ella:
→ 0$ de inversión
→ trabaja sola
→ 20 min por cliente
su padre sigue creyendo que trabaja en mcdonald's.
este es el mismo sistema, pero escalado: una máquina de captación b2b de 10k$/mes con la misma lógica, sin llamadas en frío ni anuncios ↓
guárdalo. no lo vas a volver a ver tan claro.
Erwin retweeted
See the impressive collection of @OReillyMedia Machine Learning / AI / Data Science books at: amzn.to/3icyoqJ
Erwin retweeted
INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 2 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a new skill. Watch it and bookmark it now.
Erwin retweeted
Google just dropped a 1-hour breakdown of Graph Engineering — showing how to go from one AI agent to a system that runs 24/7.
00:00 — Understanding graph fundamentals
09:16 — Build your first AI agent
21:15 — The concept of Graph Engineering
41:03 — Putting Graph Engineering into practice
52:21 — Building self-improving graphs
It’s completely free and one of the most valuable resources for anyone looking to understand where AI agents are heading.
Prompts → Agents → Loops → Graphs
Most people will watch the first 9 minutes, build a basic agent, and call it a day.
But the final 20 minutes reveal the bigger picture.
Same model.
Same tokens.
A fundamentally different level of capability.
Watch it today.
Erwin retweeted
Anthropic senior engineer just dropped a 1-hour course on building a team of agents with loops & graphs:
00:27 - claude-md & Plan mode
11:24 - skills and hooks
37:02 - agents and subagents
52:47 - self-improving loops and graphs
taught by someone who runs this inside Anthropic
Prompts → Agents → Loops → Graphs
most people stop at one agent and call it a team
he spends the last eight minutes on the loop that runs it without him
same model, same tokens, completely different week
watch it today
the full guide on building a team of self-improving agents is below, save it while it is still early ↓
Erwin retweeted
You can make $500 per day if you have:
1. A laptop
2. Wi-Fi
3. Time
Here are 10 Claude Prompts that pay you daily:
Erwin retweeted
🚨this is SERIOUSLY dangerous.
i just watched an 18-year-old calmly explain how he turned Opus 5.5 into a personal Bloomberg Terminal (traders pay nearly $32,000 a year for one), and i'm convinced 99% of people still aren't seeing this
it's the screen wall street traders stare at all day to trade the markets, and the best of them make $1M+ a year
the whole system fits in four lines:
- open a market app and pick Claude Opus 5.5 as its brain
- type in the stocks and coins you hold
- connect your Telegram
- close the laptop
from there, Opus 5.5 does all of it
every weekday at 8:00 it checks your list, catches whatever moved more than usual, digs up why and sends it to your Telegram, with a source and a time on every reason
1 question ≈ 23 sources read
zero charts
zero news tabs
zero stress
one sentence to set it up, then it runs on autopilot
you're done chasing the market
you're running your own Bloomberg Terminal
save this. the full course is below
Erwin retweeted
this is the most DANGEROUS thing on internet today
REA (Reverse Engineer Anything) - this open source MCP lets your AI agent reverse engineer any app, down to the binary
i just reverse engineered TradingView, now I am using their premium indicators for FREE - software is cooked
here is how to use REA to reverse engineer TradingView:
1. point REA at TradingView's publicly observable interface and map every major feature, from chart interactions to indicators and alerts
2. trace how the interface behaves when you switch symbols, change timeframes, add indicators, draw levels, and update chart layouts
3. use REA's available MCP tools to investigate authorized software artifacts and trace application logic wherever the evidence allows
4. feed those findings into Claude Opus 5.5, which turns the investigation into a technical specification and an implementation plan
5. rebuild the charting engine independently, with real market data, candlesticks, technical indicators, drawing tools, and persistent watchlists
6. add a quant backtesting engine that tests strategies against historical data, accounting for fees, slippage, and drawdowns
7. test every component, compare its behavior against documented and observable results, fix failures, and keep iterating until the system actually works
8. you end up building your own TradingView-style quant research terminal from scratch, with source code you control and features you can keep extending
i won’t say anything more:
Erwin retweeted
This is an actual goldmine for every AI builder
400+ ready-made agents and skills for almost any job. From Anthropic, its engineers and the community.
github.com/msitarzewski/agen… (158k stars)
~170 agents organized like a company: engineering, design, marketing, sales, product, testing, security, support. Extra packs for finance, healthcare and game dev. Works with 15+ tools.
github.com/wshobson/agents (40k stars)
202 agents, 184 skills and 105 commands packed into 94 Claude Code plugins. Language experts, code review, debugging, infra, security, testing. Install only the plugins you need.
github.com/anthropics/knowle… (26k stars)
Anthropic’s own plugins built around jobs: sales, customer support, product management, marketing, legal, finance, data.
github.com/anthropics/claude… (18k stars)
Official agents you can deploy: a daily brief from Slack and GitHub, scheduled Sentry triage, Slack and Linear bots, a customer support agent, a financial data analyst.
github.com/addyosmani/agent-… (103k stars)
From Anthropic engineer. 25 skills covering the whole dev cycle: interview-me, spec writing, TDD, browser testing, security review, CI/CD.
I’d start with claude-quickstarts. Every agent there is a full working example you can run and take apart.
Erwin retweeted
LO QUE ESTOS TIPOS ACABAN DE PUBLICAR EN GITHUB NO TIENE NINGÚN SENTIDO
un Palantir open source. se llama Osiris.
rastreo en tiempo real:
→ vuelos comerciales, privados y militares
→ satélites y la Iss
→ cámaras públicas de vigilancia
→ terremotos, incendios y fenómenos extremos
→ instalaciones nucleares y zonas de conflicto
herramientas de reconocimiento integradas, sin instalar nada:
→ escaneo de puertos
→ Dns y Whois
→ certificados Ssl
→ reputación de Ip
todo desde un globo 3d interactivo, directamente en tu navegador y totalmente gratis.
más de 1.500 estrellas en solo diez días.
el software de inteligencia acaba de dejar de ser exclusivo.
os dejo el repo abajo.
Erwin retweeted
Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run.
This beats any paid course on agents I've seen.
Watch it, then read the guide on building loops below.
Erwin retweeted
Don't waste 2 years learning to become an AI agentic engineer in 2026.
Andrew Ng, the godfather of AI, gave the complete playbook to become one from scratch.
1 hour course. Free:
• 00:00 - AI agent basics
• 12:12 - AI Agentic workflows & design patterns
• 53:27 - Practical tips for building AI agents
• 1:20:30 - self-improving AI agent loops
• 1:30:19 - multi-agent AI systems
I watched it last night.
Halfway through, I realized I could get into Anthropic in weeks, not years.
Bookmark now. Watch it. Then build your own AI agent
Erwin retweeted
this is absolutely f*cking insane
Black Rock just leaked 5 GitHub repos that give you the trading desk a fund pays millions for:
want a full research team arguing over every trade?
-> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk
github.com/TauricResearch/Tr…
want the data terminal without the terminal bill?
-> OpenBB: an open data platform for analysts, quants and AI agents
github.com/OpenBB-finance/Op…
want a bot that actually places the orders?
-> freqtrade: free, open-source crypto trading bot with backtesting built in
github.com/freqtrade/freqtra…
want the engine serious quants run in production?
-> NautilusTrader: a Rust-native trading engine where the backtest and the live run use the same code
github.com/nautechsystems/na…
want all of it in one place?
-> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading
github.com/OpenByteInc/Quant…
~282k stars of trading infrastructure. $0 in licences.
now the part worth trying.
every one of these has the same slow spot: the moment before the order, where something has to say yes or no.
that's where Jev goes.
it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds.
QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block.
the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order.
the catch: fast is not the same as right. none of this is an ATM. paper trade it first.
Jev + these five is the setup to test this month.
bookmark and share with a friend
Erwin retweeted
This might be the most valuable AI list you have seen this year
Anthropic will ask you exactly about this during the interview
Every course below is free
01 Deep Learning
Stanford CS231n. Convolutional networks, taught at Stanford.
▸ youtube.com/playlist?list=PL…
02 Fundamentals
Essence of Linear Algebra. The visual course people finish before they touch a model.
▸ youtube.com/playlist?list=PL…
03 Optimization
Stanford EE364A. Stephen Boyd, convex optimization.
▸ youtube.com/playlist?list=PL…
04 Machine Learning
Stanford CS229. Andrew Ng. Lecture 1 alone has 4.8 million views.
▸ youtube.com/playlist?list=PL…
05 Reinforcement Learning
David Silver, DeepMind. How an agent learns to act.
▸ youtube.com/playlist?list=PL…
06 Graphical Models
CMU 10-708. Eric Xing. Uncertainty as a graph.
▸ youtube.com/@CMU-10-708-PGM
07 Bayesian Deep Learning
How a model says it does not know. Variational inference, from the same map.
▸ youtube.com/results?search_q…
08 Medical Imaging
MIT 6.S897. David Sontag and Peter Szolovits. Machine learning for healthcare.
▸ youtube.com/playlist?list=PL…
09 Graph Networks
Stanford CS224W. Jure Leskovec. Machine learning with graphs.
▸ youtube.com/playlist?list=PL…
10 Language
Stanford CS224n. Chris Manning. Word vectors through to attention.
▸ youtube.com/playlist?list=PL…
11 Speech
Deep learning for speech recognition. How audio becomes text.
▸youtube.com/watch?v=g-sndkf7…
12 Computer Vision
The same Stanford CS231n, from detection through segmentation.
▸ youtube.com/playlist?list=PL…
13 RL Bootcamp
Berkeley Deep RL Bootcamp, 2017. Two days, the people who built the field.
▸ youtube.com/playlist?list=PL…
save this ⭣
Erwin retweeted
WTF, I TAUGHT MY CRAWLER TO KILL SCAM COINS, WENT TO SLEEP, AND JEV + MY GROK BOTS GOT MY $100 TO $17,608 BY NIGHT 4
1.2M of you watched my crawler trade yesterday
last night i gave it a second job, kill the rugs before they reach Jev
everyone else's crawler just reads, mine has a kill list now
a rug is a coin built so the creator can dump it on you
the crawler is a robot that scrolls the internet for me
Jev is a tiny AI judge, it only says yes or no, faster than a blink, for under a cent
crawler reads it, Jev judges it, my Grok bots buy and sell it
the crawler's new job:
it went through 81 brand new coins, stomped the fakes, dragged one survivor to Jev
the survivor:
HIGGS, nine hours old, $2.23M at 10pm, Jev said yes
the night:
→ 10:35pm in at $1.97M, out at $2.29M, +$435
→ 11:35pm a bounce faked us out, -$106
→ 2:25am the coin hit $708K, holders down 68%, Jev said buy
→ 3:10am out at $899K, +$746
→ 4:15am second bottom at $716K, crawler saw buyers return, Jev said yes
→ 5:50am sold $1.69M, +$4,404
holding it from 10pm lost you 24%
my bots made 44.8% on the same coin while i slept
honestly the stomping is what i'd pay for, most people lose money on coins they should've skipped
$100 → $2,197 → $4,962 → $12,161 → $17,608
second 20, the spider stomps a rug
i left the whole setup below ↓ free, steal it
bookmark this before night 5
send this to the friend who buys every coin he's shilled
would you hand a bot the kill switch on your coins, or do you still trust your own eyes?
Erwin retweeted
trading here: fomo.family/r/savipww
alpha here: t.me/+GrPfolvACZg2OTMy
github (projects will be here soon): github.com/blsssdsavip
Erwin retweeted
give this 24/7 stock research prompt to claude opus 5.5
it will probably make you a LOT of money...
you're welcome:
Erwin retweeted
opus 5.5 is f**king insane.
drop this into Claude Opus 5.5 and it will design your first full team of AI agents with prompts, workflows, and everything for you
save and steal this now:
