Angelo @skcaaj

> te despiertas > abres Claude > preguntas algo básico > cierras la pestaña > ves que alguien ganó $30k esta semana con Claude > te sientes mal > encuentras este post > ves la guía de 4 horas > 15 minutos después > tu cerebro hace clic > entiendes que has estado usando el 10% > arreglas todo > construyes tu primer sistema > lo pones en marcha > vas a dormir > despiertas siendo otra persona

Rodev @romandevz

2 days ago

CURSO COMPLETO DE CLAUDE 4 HORAS La guía de Claude más completa que he visto. Crea tus propias herramientas. Automatiza tu trabajo. Construye bots y sistemas de verdad. Claude → Herramientas → Automatización → Productos → Dinero Guárdalo antes de perderlo. 🔖

56 187 2K 411K 4K

Cloud sessions are officially available and out of research preview! They let you keep Claude Code working, even when your laptop is closed. Existing subscribers get a one-time credit to try them: $100 on Pro, $250 on Max.

Google engineer: “90% of engineers are still using LLMs like ChatGPT and Claude wrong. They run one agent, it fails, and they decide the model is dumb. At Google, senior engineers already use harnesses with loops and graphs to run self-learning agentic systems.” In this 18-minute session, a Google engineer explains how to build a self-improving agent harness from scratch. Watch it today if you don’t want to fall behind, then read the full guide to harness engineering below.

Ichigo @iiiichigo_chan

4 weeks ago

x.com/i/article/2093…

14 114 699 1.2M 2K

this is free f*cking gold a second brain article hit 8 million views, so the guy behind it put the entire setup in one place the repo, the guide, the tools, the learning path. all of it, free • the guide > 10 sections, 65 pages, concept through troubleshooting > 5 tracks on top, 44 pages, 15 of them build guides with code that runs • the machine (.claude/) > 18 agent skills, one per workflow > 72 slash commands - /ingest-pdf, /ingest-youtube, /ingest-voice, /backfill > 6 subagents - curator, linker, researcher, reviewer, ingestor, graph-analyst > 4 of them read only, so nothing rewrites your vault behind your back • the scripts (plain Python, zero dependencies) > graph export, link checker, vault stats, chat converter, site builder • the starter vault > its own CLAUDE.md with page contracts and linking rules > raw/ never edited after it lands, wiki/ is what the agent maintains > log.md - one line per run, so the whole thing stays auditable • 87 vetted resources > 28 tools, 26 Obsidian plugins, 15 repos, 12 skills, papers and articles five tracks to pick from: > knowledge graphs > Jev engineering > agent harnesses > loop engineering > eval engineering start with the second brain guide if you're new. go straight to the tracks if you already live in this stuff a consultant charges four figures to build you a research system. this one sits in a public repo under MIT ↳ github.com/undefined-ui/s…

Mr. Buzzoni @polydao

3 months ago

x.com/i/article/2065…

36 130 992 1.9M 3K

كورس مجاني مدته ساعة واحدة من مهندس في Anthropic يبني منظومة متكاملة من الوكلاء الذكيين! 💥👇 ​سيعوضك تماماً عن الكورسات المدفوعة لبناء وهندسة الوكلاء البرمجية ​دليل عملي شامل لبناء أسراب برمجية ذاتية التطوير والتحسين تعمل معاً بدون تدخل بشري! 🤯🚀 x.com/iansh04_/statu…

10 GITHUB REPOSITORIES THAT FEEL ALMOST ILLEGAL TO BE FREE And yes, they're all open source. 1. Archify Turn codebases into architecture, workflow, sequence and data-flow diagrams with AI. github.com/tt-a1i/archify 2. OpenMAIC A multi-agent environment where AI agents can collaborate and work together. github.com/THU-MAIC/OpenM… 3. DeepSeek Harness An open-source harness for building and running AI coding workflows. github.com/deepseek-ai/dsh 4. Ponytail A simple approach to helping AI coding agents write less unnecessary code. github.com/DietrichGebert… 5. Agent Skills Reusable skills that give AI coding agents more specialized capabilities. github.com/addyosmani/age… 6. OmniVoice Studio An open-source studio for experimenting with AI voice generation workflows. github.com/EliasGhanem/Om… 7. Scientific Agent Skills Specialized skills for AI agents working on scientific research and analysis. github.com/K-Dense-AI/cla… 8. Orca Run multiple AI coding agents in parallel inside one development environment. github.com/Orca-Technolog… 9. MiniMind A compact project for learning how language models work by building one yourself. github.com/jingyaogong/mi… 10. God's Eye View A visual project exploring how AI can understand and represent complex systems. github.com/bilawalsidhu/g… All open source. Some are useful today. Some are worth studying. Some could become much bigger. Bookmark this list for the weekend.

keyboard_arrow_left Previous keyboard_arrow_right Next

Milyarderlerin Ne Aldığını ve Ne Okuduğunu Ücretsiz Gösteren 50 Site 1.) dataroma.com → Ünlü yatırımcıların güncel portföyleri 2.) whalewisdom.com → Fonların çeyreklik alım satımları 3.) capitoltrades.com → ABD'li politikacıların hisse işlemleri 4.) openinsider.com → Yöneticilerin kendi şirket hisseleri 5.) 13f.info → Fon bildirimlerini okunur hale getirme 6.) sec.gov/edgar → Şirketlerin resmi raporları 7.) berkshirehathaway.com → Buffett'ın 1977'den beri mektupları 8.) buffett.cnbc.com → Buffett toplantılarının video arşivi 9.) oaktreecapital.com → Howard Marks'ın yatırımcı notları 10.) bridgewater.com → Ray Dalio'nun firmasının araştırmaları 11.) principles.com → Dalio'nun ilkeleri ücretsiz 12.) gmo.com → Jeremy Grantham'ın piyasa notları 13.) aqr.com → Kantitatif fon araştırmaları 14.) pages.stern.nyu.edu/~adamodar → Damodaran'ın değerleme verileri 15.) aswathdamodaran.blogspot.com → Değerleme profesörünün blogu 16.) collabfund.com/blog → Morgan Housel'in para yazıları 17.) fs.blog → Karar vermenin zihinsel modelleri 18.) am.jpmorgan.com → JPMorgan'ın ücretsiz piyasa rehberi 19.) ark-invest.com/research → Yenilik odaklı fon araştırmaları 20.) a16z.com → Girişim sermayesi denemeleri 21.) csinvesting.org → Değer yatırımı ders notları 22.) gsb.columbia.edu/valueinvesting → Columbia'nın değer yatırımı arşivi 23.) fred.stlouisfed.org → Fed'in ekonomik veri arşivi 24.) federalreserve.gov → Fed kararları ve açıklamaları 25.) ecb.europa.eu → Avrupa Merkez Bankası verileri 26.) bis.org → Merkez bankalarının bankası raporları 27.) tradingeconomics.com → Ülkelerin ekonomik göstergeleri 28.) macrotrends.net → Şirketlerin uzun vadeli grafikleri 29.) stockanalysis.com → Şirket finansalları ücretsiz 30.) companiesmarketcap.com → Şirketlerin piyasa değeri sıralaması 31.) finviz.com → Hisse tarama ve ısı haritası 32.) portfoliovisualizer.com → Portföy geri testi 33.) tradingview.com → Grafik ve piyasa analizi 34.) koyfin.com → Profesyonel piyasa ekranı 35.) annualreports.com → Şirket faaliyet raporları arşivi 36.) investor.gov → SEC'in yatırımcı eğitim sitesi 37.) bogleheads.org/wiki → Pasif yatırım ansiklopedisi 38.) investopedia.com → Finans terimleri sözlüğü 39.) corporatefinanceinstitute.com → Ücretsiz finans rehberleri 40.) cfainstitute.org → CFA araştırma yayınları 41.) morningstar.com → Fon ve hisse değerlendirmeleri 42.) simplywall.st → Şirketlerin görsel analizi 43.) valueinvestorsclub.com → Seçilmiş yatırım tezleri arşivi 44.) etfdb.com → Fonların içinde ne olduğunu görme 45.) curvo.eu → Avrupa fon geri testleri 46.) ofdollarsanddata.com → Veriyle yatırım yazıları 47.) awealthofcommonsense.com → Piyasa tarihi notları 48.) theirrelevantinvestor.com → Yatırımcı psikolojisi yazıları 49.) visualcapitalist.com → Ekonomiyi grafiklerle anlatma 50.) ourfiniteworld? → (bkz. not) Zenginler bilgiyi saklamıyor. Sadece nerede durduğunu kimse söylemiyor. Kaydedin, lazım olur. Yatırım tavsiyesi değildir.

🚨 ALGUIEN ACABA DE OPEN-SOURCEAR ELEVENLABS Y LO PUEDES CORRER EN TU PROPIO ORDENADOR se llama VoiceStudio, casi 20k estrellas en GitHub ya → le das un fragmento de voz humana limpia y aprende esa voz → dobla vídeos a 646 idiomas → audiolibros, dictado, transcripción de voz a texto, todo lo hace → 14 motores distintos, no uno solo, ElevenLabs solo tiene 32 idiomas → no cobra por carácter, no hay límite de usos, y el audio ni se sube alguien lo probó con una 5090 y dice que aún le falta un poco de pulido, pero esto es gratis y la voz se queda en tu ordenador, ¿qué más se puede pedir? Tienen la repo abajo👇🏻

tu viendo a usuarios de Claude automatizar negocios enteros sacando $10k, $50k, $100k al mes, mientras sigues escribiendo prompts a mano pero alguien soltó una guía completa de 4 horas sobre cómo lo hacen

draven @dravenip

4 days ago

Anthropic just launched a free 4-hour course. It teaches you to use Claude with the same workflows their own engineers use internally. 00:15 → How to structure prompts for Claude the right way 11:41 → The "output contract" that fixes inconsistent responses 30:04 → The loop

11 64 323 249K 805

Bitcoin at $85K: What’s Driving the Next Move? [Ft. Nic Puckrin] #CHAINREACTION x.com/i/broadcasts/1…

a Stanford professor used JEV to build a data science system that analyzes 40.000.000.000 data points every 15 min his system can process massive datasets and automatically decide which results deserve deeper analysis. the professor spent more than a year developing the system with his research team. the first version relied heavily on LLMs to interpret every result. it worked, but analyzing millions of records created unnecessary latency and huge inference costs. then they redesigned the decision layer around Jev. instead of generating explanations for every data point, Jev evaluates the results and decides what the system should investigate next. I found a breakdown of the pipeline they used and the way Jev filters the data is surprisingly clever. I’ll show you how it works next so stay tuned if you want to see what Jev Engineering looks like inside a real data science system. would you let an AI decide which patterns in your data are worth investigating?

barnyx @me_barnyx

4 days ago

x.com/i/article/2101…

18 27 197 218K 415

Este cara em apenas 16 minutos te ensina como monetizar um canal do YouTube em 12 dias

FELPS @FelpsCrypto

4 weeks ago

Se eu começasse do ZERO hoje, sem aparecer e sem equipe, esse seria meu plano para tentar construir um canal faceless de US$21K/mês usando IA. Coloquei estratégia, prompts, roteiro, thumbnails e o sistema completo. Salva isso. 🚀 x.com/i/article/2093…

9 28 399 396K 921

Redis built a cache that cuts LLM costs by 70%! Production LLM apps often receive different versions of the same question. For instance, an internal developer assistant might receive: - "How do I rotate an API key?" - "Where can I replace my API key?" The wording is different, but both questions have the same answer. Prefix caching cannot handle this repeated generation because it only reuses computation when the cache matches bit-by-bit. And if the cache hits, an LLM response is still generated again. A semantic cache stores the complete question-response pair outside the model. When a query arrives, it searches for previously answered questions with similar meaning. A valid match returns the stored response with no LLM call. If you want to use this in practice, @Redisinc already implements it as a managed service called Redis LangCache. Under the hood, LangCache embeds the incoming question, searches stored responses, and applies the configured similarity threshold and filters. A cache hit returns the earlier response. A miss falls back to the LLM, after which the new response can be stored for future requests. Redis also handles access scopes, custom filters, embedding selection, TTL, eviction, and monitoring through a REST API, without another database to deploy or manage. While the actual savings depend on how much safe repetition exists in the workload, cache-hit responses are up to 15x faster and 70% cheaper. Try Redis LangCache: fandf.co/4d3ixqL I built a small interface comparing LangCache with direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put it together. To dive deeper, my co-founder published a detailed article on KV, prefix, prompt, and semantic caching. Read it below.

Avi Chawla @_avichawla

4 weeks ago

x.com/i/article/2093…

24 191 1K 1.6M 3K

Stanford AI engineering course: "Anyone can build an AI agent in 60 minutes" Prompt → Agent → Loop → Decision layer Stanford just released a course on building AI agents from scratch 00:00 - Build your first AI agent 48:13 - Create agents without coding 54:33 - Ship one that runs while you sleep the hour gets you an agent that works. the layer above it is what keeps it cheap once it runs all day every fork inside that loop is still a full frontier call until you move it This free course is better than most paid AI agent courses Bookmark and watch it today Then read the article below

Hanako @hanakoxbt

a month ago

x.com/i/article/2091…

51 221 1K 5.4M 5K

🚨 لو بتفكر تبني مشروع على الإنترنت، الفيديو ده يستاهل 25 دقيقة من وقتك. شاب بيشرح بالتفصيل إزاي بنى 3 مواقع إلكترونية ووصل بيها لأكثر من $100,000 شهريًا. والأهم إنه مش بيحكي النتيجة بس، لكنه بيمشي معاك في الرحلة: Idea → Build → Monetize من اختيار الفكرة، لبناء الموقع، وبعدها إزاي تحوله لأصل رقمي بيحقق دخل. سواء أنت مطور أو عندك فكرة مشروع، الفيديو ممكن يوفر عليك وقت وتجارب كتير. 📌 اعمله Bookmark وشوفه لما تكون فاضي x.com/deanwperkins/s…

Claude Code es un rollo. Hasta que instalas esto. Hay un plugin oficial de Anthropic llamado claude-code-setup. Te dice qué automatizaciones puedes montar (hooks, skills, MCP servers, subagentes...) у cómo configurarlas paso a paso. Básicamente analiza tu proyecto y te recomienda qué activar. Para instalarlo: / plugin install claude-code-setup@claude-plugins-official Guarda este post para no perderlo 📩

A Russian guy has discovered a method to learn anything ten times faster using AI! It involves NotebookLM, Gemini and Obsidian.

Vous cherchez une alternative gratuite à Higgsfield ou OpenArt pour créer des pipelines d'IA ? HeliosGen est la solution ! Auto-hébergée, elle vous permet de gérer visuellement vos invites, modèles et automatisations sur un canevas infini. Quelle fonctionnalité vous a le plus impressionné dans HeliosGen ? github.com/segfault42/hel…

pure f*cking treasure: 5 github repos that quietly replace tools people pay thousands for ~ free for dev (131k stars): hundreds of services with a permanent free tier, no trials, that's the repo's own rule github.com/ripienaar/free… ~ public apis (453k stars): 1500+ free apis for weather, finance, images, games github.com/public-apis/pu… ~ awesome selfhosted (309k stars): self hosted replacements for notion, google photos, zapier and dozens more subscriptions github.com/awesome-selfho… ~ awesome claude code (51k stars): skills, hooks, slash commands and orchestrators for claude code github.com/hesreallyhim/a… ~ anthropics skills (165k stars): the official skills repo, start here before any third party one github.com/anthropics/ski… bookmark this before you pay for something that's already free

wluha @cryptowluha

a week ago

x.com/i/article/2099…

2 5 24 215K 45

x.com/i/article/2090…