Triuzla retweeted
Google just dropped a 1-hour course on agentic engineering from scratch:
00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems
This 1-hour watch will replace 10 paid agentic courses on the internet.
Bookmark this. Watch this weekend.
Triuzla retweeted
This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid graduating high school should do now. His answer:
"It will also eliminate jobs, and probably a large number of them"
In 35 seconds, he names who gets hit first: entry-level law, entry-level finance, entry-level consulting
His own prediction: 50% of entry-level white-collar jobs disrupted in 1 to 5 years
Every past disruption gave people time to adapt. He says this one is deeper and coming faster
Prompts → Agents → Harness → Loops → The One Running the AI
His advice: learn to use AI. Using it won't be enough. You need a harness that runs it for you
You can start with repos bellow.
Every repo below is free:
Anthropic's plugins for legal, finance, sales, HR and data work
github.com/anthropics/knowle…
Anthropic's agents for analyst work: models, memos, research notes
github.com/anthropics/financ…
Excel, Word, PowerPoint and PDF skills
github.com/anthropics/skills
Autonomous financial research agent
github.com/virattt/dexter
Deep research agent
github.com/assafelovic/gpt-r…
Full-length research reports
github.com/stanford-oval/sto…
12 principles of agents that actually work
github.com/humanlayer/12-fac…
Batteries-included agent harness
github.com/langchain-ai/deep…
Claude Agent SDK
github.com/anthropics/claude…
Agent memory
github.com/thedotmack/claude…
Autonomous agent loop
github.com/snarktank/ralph
Browser control
github.com/microsoft/playwri…
Claude cookbooks
github.com/anthropics/claude…
Free agents course: 18 lessons
github.com/microsoft/ai-agen…
All of this costs $0
AI won't replace you. Someone with a harness will
95% will keep applying for jobs AI already does, the 5% who build a harness will be the ones running it
Bookmark it and send it to someone just starting their career
Then use the guide below to build your harness before everyone else does ↓
Triuzla retweeted
STOP WASTING HOURS TRYING TO FIGURE OUT WHAT TO LEARN IN AI.
I put together one practical roadmap with videos, GitHub repos, guides, books, research papers, and courses.
VIDEOS:
1. LLM Introduction — youtube.com/watch?v=zjkBMFhN…
2. LLMs from Scratch — youtube.com/watch?v=9vM4p9NN…
3. Agentic AI Overview (Stanford) — youtube.com/watch?v=kJLiOGle…
4. Building & Evaluating Agents — youtube.com/watch?v=d5EltXhb…
5. Building Effective Agents — youtube.com/watch?v=D7_ipDqh…
6. Building Agents with MCP — youtube.com/watch?v=kQmXtrmQ…
7. Building an Agent from Scratch — youtube.com/watch?v=xzXdLRUy…
8. Philo Agents — youtube.com/playlist?list=PL…
GITHUB REPOS:
1. GenAI Agents — github.com/nirdiamant/GenAI_…
2. Microsoft AI Agents for Beginners — github.com/microsoft/ai-agen…
3. Prompt Engineering Guide — github.com/dair-ai/Prompt-En…
4. Hands-On Large Language Models — github.com/HandsOnLLM/Hands-…
5. GenAI Agents — github.com/NirDiamant/GenAI_…
6. Made with ML — github.com/GokuMohandas/Made…
7. Hands-On AI Engineering — github.com/Sumanth077/Hands-…
8. Awesome Generative AI Guide — github.com/aishwaryanr/aweso…
9. Designing Machine Learning Systems — github.com/chiphuyen/dmls-bo…
10. Machine Learning for Beginners — github.com/microsoft/ML-For-…
11. LLM Course — github.com/mlabonne/llm-cour…
GUIDES:
1. Google's Agent Whitepaper — kaggle.com/whitepaper-agents
2. Google's Agent Companion — kaggle.com/whitepaper-agent-…
3. Building Effective Agents by Anthropic — anthropic.com/engineering/bu…
4. Claude Code Agentic Coding Practices — code.claude.com/docs/en/best…
5. OpenAI's Practical Guide to Building Agents — cdn.openai.com/business-guid…
BOOKS:
1. Understanding Deep Learning — udlbook.github.io/udlbook/
2. Building an LLM from Scratch — manning.com/books/build-a-la…
3. The LLM Engineering Handbook — oreilly.com/library/view/llm…
4. AI Agents: The Definitive Guide — oreilly.com/library/view/ai-…
5. Building Applications with AI Agents — oreilly.com/library/view/bui…
6. AI Agents with MCP — oreilly.com/library/view/ai-…
7. AI Engineering — oreilly.com/library/view/ai-…
RESEARCH PAPERS:
1. ReAct — arxiv.org/abs/2210.03629
2. Generative Agents — arxiv.org/abs/2304.03442
3. Toolformer — proceedings.neurips.cc/paper…
4. Chain-of-Thought Prompting — arxiv.org/pdf/2201.11903
COURSES:
1. Meta Data Analyst Professional Certificate: imp.i384100.net/rENKMG
2. Google Advanced Data Analytics Professional Certificate: imp.i384100.net/jR67bn
3. Microsoft Power BI Data Analyst Professional Certificate: imp.i384100.net/PzdQx6
4. Google Data Analytics Professional Certificate: imp.i384100.net/xJ6DQx
5. Introduction to Data Analytics: imp.i384100.net/5k0drn
6. Machine Learning Specialization: imp.i384100.net/k42K6M
7. IBM Deep Learning with PyTorch, Keras and Tensorflow Professional Certificate: imp.i384100.net/enZ0zg
8. Deep Learning Specialization: imp.i384100.net/qW6KMO
9. Crash Course on Python: imp.i384100.net/QYd9Dz
10. Python for Data Science, AI & Development: imp.i384100.net/9Vd6kQ
11. ChatGPT + Excel: AI-Enhanced Data Analysis & Insight Specialization: imp.i384100.net/rENKMB
12. Work Smarter with Microsoft Excel: imp.i384100.net/jR67ba
13. Microsoft Excel Professional Certificate: imp.i384100.net/PzdQxq
14. Excel Basics for Data Analysis: imp.i384100.net/5k0drD
15. SQL Foundations: imp.i384100.net/k42K6v
Repost so someone else can find this roadmap, and pls consider following @Mohiniuni for more content around AI, Beauty, and businesses.
Triuzla retweeted
THIS IS F*CKING INSANE
SpaceXAI just dropped 146 Grok Bot templates worth $29,200 for FREE
bots like these basically cost $50–$200 each. and that’s just the official collection. GitHub already has 700+ bots, including complete teams with specialist roles, ready-made handoffs, and separate verifiers
20 GitHub projects you should open first:
01 Agent Org Chart → ready-made team structures for engineering, marketing, support, and sales. pick the organization your job needs instead of inventing every role
github.com/serenakeyitan/age…
02 Grok Factory → one Firstmate routes software, research, and general work to the right specialists, then brings back reports or reviewed pull requests
github.com/jaredtrichard/gro…
03 multiBot → creates purpose-built teammates that delegate heavy work to coding CLIs, keeping Grok Bot focused on coordination and returning the result
github.com/simo255/multiBot
04 Grok Bot Architecture → a blueprint for a chief of staff, specialist bots, structured handoffs, connected tools, and human approval points on one shared computer
github.com/tiagovilasboas/gr…
05 Foreman → inspects a hosted bot crew, surfaces stalled work, and records evidence behind completion claims. a separate checker supplies the passing verdict
github.com/Archive228/forema…
06 Grok Bot Second Brain → a five-bot setup with Conductor, Capture, Memory, Ops, and Research, sharing a knowledge vault and defined responsibilities
github.com/mKay00/grok-bot-s…
07 grokbot-skills → reusable skills for debugging, brainstorming, writing, and observing tasks, with upstream sources and licenses preserved
github.com/jeremybrasher/gro…
08 grokbot-x → an X content workflow that scouts posts, prepares drafts, publishes through Typefully, and uses logged results to evaluate changes to its writing skills
github.com/YannisKiefer/grok…
09 Restaurant Scout → a specialist setup for finding food brands and creators, preparing shoppable-content scripts, and organizing the findings into a catalog workflow
github.com/mykemueller1-ctrl…
10 Grok Bot Shopping → shopping skills for product search, merchant checkout, Shopify discount-code tests, and order workflows, plus an optional Buyer bot
github.com/steve228uk/grok-b…
11 PhoneZero → gives Grok Bot a phone workflow for tasks like restaurant bookings. it prepares the call plan, waits for approval, and reports the outcome
github.com/function1st/Phone…
12 Unlist → a privacy assistant playbook for people-search opt-outs, with site records, letter generation, submission logs, and follow-up tracking
github.com/shawnyeager/unlis…
13 Grok Bot Gateway → lets coding agents and scripts list bots, read conversations, and send tasks through a gateway bot using a webhook routine
github.com/dimpurr/grok-bot-…
14 grokbot-queue → queues and dispatches tasks across multiple Grok Bots, then collects their results using SSH and unofficial desktop automation
github.com/ShuhangGe/grokbot…
15 Thin Grok Bot → a delegation skill that keeps the bot team focused on routing while deeper builds and investigations run through coding CLIs or cloud agents
github.com/Luca-Blight/thin-…
16 BOTROSTER → a separate self-hosted alternative with persistent named teammates, shared files, a browser, scheduled work, and approval controls
github.com/mandarwagh9/botro…
17 Root Agent → a coordinator that determines which specialists a request needs, manages assignments, and hands domain work to leads
github.com/MrBekoX/root-agen…
18 Grok Bot Profiles → four focused roles: Spec Writer, Bug Reproducer, PR Producer, and PR Verifier. implementation and verification stay in separate conversations
github.com/HAEGONG/grok-bot-…
19 Grok Bot Templates → 49 templates with defined jobs, outputs, skills, routines, and boundaries, plus team setups you can adapt to your work
github.com/cobusgreyling/gro…
20 HyperGrok Trading Desk → seven bots covering market data, research, strategy, risk, execution, and review. starts in research mode; live trades require your approval
github.com/galleonlabs/hyper…
give the first team a job with an obvious finish line: one researched brief, one reviewed PR, or one prepared batch of drafts
then check how much work you actually accepted and what it cost to produce. a larger roster earns its place when it improves that result
the setup can be free. paying several bots to repeat the same investigation still costs you
save this before you spend another weekend building a workflow that already exists
the article below shows how to keep context smaller, reuse completed work, and contain retries so more of your Grok Bot budget reaches the finished result ↓
HOLY SH*T, ELON MUSK PUT SPACEXAI'S BEST ENGINEERS ON A LIVE STREAM TO SHOW EXACTLY HOW TO BUILD A COMPANY WITH GROK BOTS
they start from an empty github org and zero bots. 72 hours, live.
how to use grok bot, from their demo:
step 1: make one bot per job, not one chat per task
step 2: tell it the result you want, voice works too
step 3: set approval rules, e.g. ask me before sending any email
step 4: show it a task once on screen, it saves it as a skill
step 5: add a routine, e.g. every morning at 9 it sends you a summary
step 6: if it refuses or asks questions, teach it, it keeps that in memory
the parts worth watching:
11:29 - the first hires: which bots they pick
20:23 - building a bot from scratch with one voice prompt
22:54 - teaching a bot a task by doing it once
25:21 - setting up a 9 am routine
save this and study the article below, it has ready-made grok bot configs you can copy ↓
Triuzla retweeted
Everyone is all excited about selling data to LLM companies. Science data is very poor, and much of it conflicts. I have a plan to create the world's most accurate science data. Bad data regurgitated and re-ingested is called model collapse. It's cholera for LLMs. @grokipedia certainly isn't going to do it. I claim there's only one way to fix it. Are there any investors interested in this? I'd love to talk with anyone interested in science data.
@Diegopasini @brandonguo @colingardiner @deepmind @Winston_W_Ma @saranormous @bgurley @chamath @pmarca @avc @xdotli @patrickc @alexwg @stephen_wolfram @natolambert @shaunmmaguire @NWischoff @elonmusk @rauchg @_sholtodouglas @deedydas @CompleteSkeptic @mattwridley @patrick_oshag @HarryStebbings @demishassabis @8vc @radicalvcfund @dougleone @emily_yu @SpaceXSI @david_r_so
Triuzla retweeted
Wake up.
Every profession deemed white-collar, the middle class dream, is about to be decimated by AI, at a much faster pace than anticipated, with monstrous social consequences.
Triuzla retweeted
🇺🇸 BREAKING: The US OCC finalizes GENIUS Act rules for stablecoin issuers, covering reserves, redemptions, and custody.
Effective January 18, 2027.
Triuzla retweeted
In just 8 months, Russia has killed and wounded more Ukrainian civilians than in all of 2025.
I stressed this during the Interactive Dialogue with the UN High Commissioner for Human Rights on the situation in Ukraine.
❗️July alone saw 437 civilians killed and 2,610 injured — the highest monthly toll since May 2022.
Russia’s attacks on civilians and critical infrastructure must be documented, condemned and met with accountability.
WHOEVER LEAKED THIS HAS ZERO FEAR
SOMEONE CONNECTED 350 GROK BOTS TO RUN A ONE-PERSON TRADING DESK.
I thought it was just another AI experiment until I saw the setup.
One bot scans the market.
Another hunts for setups.
Another analyzes news and sentiment.
Another tracks whales and on-chain activity.
Another manages risk and exposure.
Then a HEAD OF DESK Grok coordinates everything and sends the owner only the trades that actually need approval.
No team of analysts. No staring at charts all day.
Just 350 Grok bots passing information between each other 24/7.
The craziest part?
The owner said he barely touches the system anymore.
FULL GUILD ON HOW TO BUILD IT BELOW
Triuzla retweeted
He made $100 million in a single day while cameras were rolling, then spent years trying to erase every copy of the film.
In 1987 a 32-year-old named Paul Tudor Jones was running $125 million out of a small New York office. A PBS crew followed him for months as he stared at one chart: the 1920s Dow overlaid on the 1980s. Correlation: 92 percent.
He told them the market would climb toward 3,200, then produce an “earth-shaking” crash that would dwarf anything in living memory. Ten months later Black Monday arrived. The Dow dropped 22.6 percent in one session. Almost the entire Street was wiped out.
Jones made roughly one hundred million dollars that day.
Afterward he did everything possible to kill the documentary. He bought every VHS copy he could find and demanded PBS stop airing it. For decades the only way to see *Trader* was through bootlegs that changed hands for hundreds of dollars among traders who treated it like sacred text.
Inside the footage he delivers the single rule that actually built the fortune: “I risk 10 cents to make eight bucks.” Everything else is noise.
The full hour is free on YouTube right now. Seventeen thousand views.
Almost no one currently managing serious money has ever watched it.
This media is unavailable
Triuzla retweeted
Russia has designated me as a “terrorist” for refusing its demands for mass surveillance and censorship on Telegram.
Under Russian law, I’m banned from “publishing information on the Internet” 😌
Russian officials are clearly confused about who can ban whom from the Internet 😉
Triuzla retweeted
In 2008, Malcolm Gladwell explained why some people succeed and some don't in a single 1-hour talk.
This will permanently change the way you think about talent, effort, and success.
Bookmark & watch today, no matter what.
Google Cloud AI engineer just showed how they go from idea to deployed app at Google in 30-minutes using Claude.
26-minutes. free. by Google AI team.
one person + Claude + Google Cloud = a full engineering org running on a laptop.
worth more than any $500 vibe-coding course.
Triuzla retweeted
Starting today, users can join the initial waitlist for the Personal Computer program.
We will provide support and resources for the initial cohort.
perplexity.ai/personal-compu…








































