Wellington Holanda @welldoads

@divyansh_1729 selftrackr.vercel.app this >>😍😭

nerds, thank me later... systemdesign.io

Cloudflare has deployed default web application firewall (WAF) protections for newly disclosed PHP vulnerabilities before public disclosure. The rules use request and response signals to stop exploit attempts and prevent exposed data from reaching attackers. cfl.re/488w8dc

Vejo uma preocupação cada vez maior das empresas com a governança de modelos e agentes de IA. O benefício e o ganho de produtividade já estão claros. Agora é preciso controlar o nível de risco, os acessos, a autonomia dos agentes e governar bem os dados que passam por esses sistemas. Quanto mais autonomia a IA ganha dentro das empresas, mais importante se torna a governança. #ia

Quem lembra do Watson da IBM vencendo o Jeopardy!? #ibm #ia

@WillDobrev Com certeza C e C++.

@thallisribeiro Ele lista editais de outros portais? Infelizmente nem todos processos estão no PNCP.

Introducing TimesFM-3, a state-of-the-art time series foundation model that enables accurate multivariate time series forecasting in a single forward pass, significantly outperforming other forecasting models across major benchmarks. More on the blog →goo.gle/4x5WGpD

@BerkayB65764 @mertcobanov Ele não deleta os arquivos, apenas desativa a visualização.

@andrevalentim_ Essa aqui eu também gostaria muito de saber.

FULL COURSE 1 HOUR (Build & Automate Anything)

Harvard just open-sourced its entire ML Systems curriculum. Free. Public. 6 pillars. Hundreds of pages. And it won't get most data scientists any closer to a $150K AI role. Here's why.

“Muito obrigado. Vocês me ajudaram a realizar este sonho. Estou muito orgulhoso de vocês. À minha família, eu amo vocês. Aos fãs, obrigado por continuarem me lembrando de quem eu sou. Eu não teria conseguido isso sem vocês. Grazie! GRAZIE!” #formula1 #ferrari #f1

Lewis Hamilton venceu o GP de Barcelona 2026 e encerrou um jejum de quase 2 anos sem vitória. No rádio emocionado, Hamilton disse:

If I had to learn AI agents in 7 days, I would not read a single paper. I would build from these 10 GitHub repos. 1. awesome-llm-apps The starting point. 100+ working agent apps you can clone and run on day one. 106K+ stars. Repo → github.com/Shubhamsaboo/a… 2. AI-Agents-for-Beginners Microsoft's free 12-lesson course. Real code, real exercises, no theory dump. Repo → github.com/microsoft/ai-a… 3. CrewAI Build your first multi-agent crew in under 3 hours. Used by 60% of the Fortune 500. Repo → github.com/crewAIInc/crew… 4. LangGraph The orchestration layer every production AI system runs on in 2026. The skill on every senior AI engineer job description. Repo → github.com/langchain-ai/l… 5. awesome-mcp-servers MCP is the agent-tool standard in 2026. Plug your agent into 100+ tools without writing integrations. Repo → github.com/punkpeye/aweso… 6. OpenHands Study a real autonomous coding agent that ships pull requests on its own. Repo → github.com/All-Hands-AI/O… 7. Smolagents Hugging Face's minimal agent framework. ~1000 lines. The cleanest way to understand how agents actually work. Repo → github.com/huggingface/sm… 8. Pydantic AI The type-safe agent framework production teams are migrating to. Best choice for shipping reliable agents at work. Repo → github.com/pydantic/pydan… 9. OpenAI Agents SDK The official OpenAI framework for handoffs, tool calls, and conversation context. Repo → github.com/openai/openai-… 10. Letta (formerly MemGPT) Agents that remember. Long-term memory, self-editing prompts, persistent identity. Repo → github.com/letta-ai/letta Here's the wildest part: You don't need a paper, a PhD, or a course. You need a laptop, 7 days, and these 10 repos. The skill that pays $200K in 2026 is not understanding agents. It is shipping them. Day 1 you clone. Day 7 you have a working agent. The rest is iteration. Save this before you forget. 100% free. 100% open source.

keyboard_arrow_left Previous keyboard_arrow_right Next

This Chinese guy built a Second Brain in Obsidian and every morning gets 3 trading ideas that brought him $180,000 in 6 months. Inside he runs a pipeline of 6 workflows on N8N that automatically pulls every read article, listened podcast, and voice note into a shared Obsidian vault, and a neural network analyst every morning at 6:00 finds connections between the fresh and the old and puts the 3 strongest trading ideas for the day into the inbox. No analytics desk, no Bloomberg terminal, no Telegram chats with traders. Just a Mac Mini by the wall, an iPhone in the pocket, and 1 local Obsidian vault. And traditional quant funds keep entire teams of 8 people on salary for the same flow of insights, while his expenses are only subscriptions to Readwise, Whisper API, and N8N hosting. 6 pipelines process about 200 sources a day and close the monthly API bill at about $120. The Mac Mini itself stores the entire vault and keeps the neural network analyst running 24/7, and from the iPhone the owner drops any idea he hears on the go into a Telegram bot, and it lands in the vault inbox in just 30 seconds. The starting instruction that sits in the VAULT.md file at the root of his vault looks like this: "you are the AI analyst of a solo trader. you read his vault every morning at 6:00, find connections between fresh and old notes, and deliver 3 trading ideas he can verify in the hour before the market opens. pipelines: // Reader (pulls every article and highlight from Readwise, Twitter bookmarks, and Kindle into /notes) // Listener (transcribes podcasts through Airr and voice notes through Whisper, puts them in /notes) // Catcher (accepts any message from the Telegram bot and writes it to /inbox with a timestamp) // Connector (every night reads across the entire vault and updates the connection graph between 4,000 notes) // Briefer (at 6:00 AM writes a brief: 3 trading ideas for today plus the emerging thesis of the week, puts it in /inbox) // Mobile (lives in the iPhone, answers any question about the vault by voice, and confirms alerts while the owner is on the go). you wake the owner with a push notification only when a fresh note contradicts his active thesis or when 1 of the 3 morning ideas has a confidence score above 90%." This instruction immediately sets the role for the system and the limits of its autonomy. It knows it is supposed to connect new with old on its own. It knows it is supposed to prepare 3 trading ideas every morning on its own. It knows it connects the live trader only when a thesis is contradicted or an ultra-confident idea appears. → Reader pulls about 80 articles and highlights a day from Readwise, Twitter, and Kindle → Listener transcribes 4 to 6 podcasts a week through Airr and Whisper → Catcher intercepts all voice and text ideas through the Telegram bot, averaging 15 to 20 a day → Connector updates the connection graph between 4,000 notes every night, adding 25 to 30 new edges → Briefer puts a fresh brief with 3 trading ideas and the emerging thesis into the inbox at exactly 6:00 → Mobile answers any question about the vault by voice and confirms alerts right from the iPhone And only when a new note contradicts his active thesis or 1 of the ideas breaks 90% confidence does the orchestrator raise the owner with a push notification. And when the trader at that moment is driving to the gym or eating breakfast, the Mobile agent in his iPhone answers any quick question about the vault by voice: what he wrote about this ticker last week, which 3 sources support the idea of long NVDA, and what counter-thesis already sits in his notes. The trader makes the decision and sends the order before New York opens. The fresh brief from last Monday looks like this: "reader: 78 materials added over the weekend, 11 of them about semiconductors, 4 about energy, 3 about biotech. passing to connector." "connector: 27 new connections found between fresh materials and the vault, the strongest one is that the Goldman report from Wednesday matches the NVDA thesis you wrote 3 weeks ago." "briefer: 3 trading ideas for today: long NVDA (confidence 0.84), short Tesla at the close of the quarterly report (0.71), watch URI (0.62). emerging thesis of the week: the market is underpricing capex on data centers." "alert: your fresh note about long-term risk in semis contradicts the NVDA thesis. sending for review." In his work setup there is no cloud server, no team of analysts, and not even a Bloomberg subscription. At home sits a Mac Mini with a local Obsidian vault, on top run 6 N8N pipelines and a neural network analyst, and the same vault mirrors to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo trading setup on a second brain: $120 a month on the API, about $30,000 a month into the account, and between them 6 pipelines, 4,000 connected notes, and 1 iPhone in the pocket.

CyrilXBT @cyrilXBT

6 months ago

x.com/i/article/2052…

120 503 4K 3.6M 15K

Obsidian + Claude Code = 24/7 personal operating system. Works while you sleep. The people who build this tonight will never work the same way again. Watch it and Bookmark it now.

CyrilXBT @cyrilXBT

6 months ago

x.com/i/article/2052…

120 503 4K 3.6M 15K

MIT just quietly dropped a free AI curriculum that puts $50,000 university courses to shame. 12 books. Zero tuition. From the same institution that produced the people building the models everyone is talking about. FOUNDATIONS 1. Foundations of Machine Learning — lnkd.in/gytjT5HC 2. Understanding Deep Learning — lnkd.in/dgcB68Qt 3. Machine Learning Systems — lnkd.in/dkiGZisg ADVANCED TECHNIQUES 4. Algorithms for ML — algorithmsbook.com 5. Deep Learning — lnkd.in/g2efT6DK REINFORCEMENT LEARNING 6. RL Basics (Sutton & Barto) — lnkd.in/guxqxcZZ 7. Distributional RL — lnkd.in/d4eNP-pe 8. Multi-Agent Systems — marl-book.com 9. Long Game AI — lnkd.in/g-WtzvwX ETHICS & PROBABILITY 10. Fairness in ML — fairmlbook.org 11. Probabilistic ML Part 1 — lnkd.in/g-isbdjj 12. Probabilistic ML Part 2 — lnkd.in/gJE9fy4w This is a complete MIT-level AI education. Not a YouTube playlist. Not a Twitter thread full of fluff. Textbooks written by the researchers who built the field. The people who actually study this will not just understand AI better than their peers. They will understand it better than most people currently getting paid to work in it. Most people will bookmark this and never open it. The ones who open it tonight are the ones who show up in 12 months having built something nobody around them understands yet. Bookmark this. Open the first one tonight. Follow @cyrilXBT for more resources that actually compound.

THIS GUY REPLACED EVERY SUBSCRIPTION FOR OVER 30 SERVICES WITH A HOMELAB HE BUILT USING CLAUDE CODE he built his own self hosted version of basically every service you pay for online and runs it all from a 27U server rack in his house the goal was simple: stop renting access to your own data, stop paying monthly subscriptions for things you can run yourself, and have one private dashboard that controls everything in your digital life he opens one homepage on his browser and from there he can: > stream his entire movie and TV collection through plex or jellyfin > request a new movie through overseerr and watch it appear in his library automatically once it's downloaded and tagged > back up every photo he takes through immich (his own google photos) > store all his files through nextcloud (his own google drive) > manage his audiobooks, ebooks, music, RSS feeds, recipes, and bookmarks from one place > block ads across his entire network with adguard home > see live grafana stats for every machine running in his house at any moment and a lot more the homepage dashboard even shows the current weather, his calendar, system stats, download queues, library counts, and shortcuts to every service he uses the hardware list: > netgate 1100 router running pfsense+ for firewall, DHCP, DNS, and VLANs > tp-link 8 port managed switch > tp-link archer C6 access point > raspberry pi 4 dedicated to a full screen grafana dashboard > HP laptop with i3 11th gen and 24GB RAM running proxmox VE as the main hypervisor > compaq laptop with a core 2 duo and 4GB RAM running proxmox backup server > tower PC with a core 2 duo running unraid for the NAS the proxmox VE box runs every self hosted service inside a debian VM with docker compose. backups run on a schedule with chunk based deduplication. unraid handles all the storage with mixed drive sizes and a single parity drive every device is on a tailscale tailnet so he can hit anything from anywhere in the world without poking holes in his firewall then he built his own private streaming empire on top of it: > plex and jellyfin pointing at the same library > overseerr to request movies and shows > radarr, sonarr, lidarr, readarr managing different media types > prowlarr indexing everything > sabnzbd and qbittorrent handling the downloads > bazarr pulling subtitles automatically > tautulli for plex stats > trailarr for trailers then the rest of the stack: > nextcloud replaces google drive > immich replaces google photos > paperless-ngx for OCR document management > adguard home blocks ads across the entire network > miniflux for RSS, karakeep for bookmarks > mealie for recipes, navidrome for music, audiobookshelf for audiobooks > calibre for ebooks, code server for VS code in the browser > stirling PDF, IT tools, microbin, searxng, pairdrop every service surfaces through homepage, a self hosted dashboard he built tooling around to auto generate the YAML config (made with claude code) this guy is paying $0 a month for what most people pay $200+ in subscriptions for and had an initial setup cost of ~1000 to 1500 USD the homelab community is quietly the most overpowered and cracked group of builders on the internet

keyboard_arrow_left Previous keyboard_arrow_right Next