Granite

@max_bevza yeah he's actually a legend

@Granite0x legend for this open source move

He built a CLI you can pipe any task through, to any AI model. instead of keeping his 255 prompt-patterns private, he open-sourced them all. Daniel Miessler. Cybersecurity researcher turned AI-tools builder. 16K GitHub followers. Runs the "Unsupervised Learning" newsletter. 'fabric' - CLI with 255 pre-built AI prompts for specific tasks. Pipe text through a pattern - AI does the work. Works with any LLM. 42,998 stars. MIT. → github.com/danielmiessler… bookmark it. This is how your terminal becomes an AI power tool.

@RohOnChain btw the website is actually dope roan thanks for the alpha as always

This is the best site on the internet to learn loop engineering. Free. Completely. Most AI engineers have never heard the term. aibuilderclub.com/blog/loop-engi… Bookmark this site. Then read this setup ↓

@sairahul1 honestly for some reason i had a feeling they'd push it back again 😄

Fable 5 goes pay-per-use in 7 days (yeah they extended it again lol) Most people will lose access and move on. The smart ones are doing something different right now. They're making Fable 5 train its own replacement — before it's gone. Tell it it's a "retiring principal engineer" leaving a complete skill library behind for the team. → It audits your repo like an incoming senior engineer. → Writes 10–16 SKILL files: debugging playbooks, change rules, the failure stories that cost real time. → Opus and Sonnet then run that playbook, at Fable's standard on cheaper sessions. Fair warning: this run eats 30% of your weekly Fable usage. Still worth it. Full prompt and the complete playbook below ↓ Bookmark this before Fable 5 goes behind credits.

@milesdeutscher thanks for showing me this article gotta read it today

One of the best articles I've read on using AI in financial markets. If you're wondering where to start with incorporating AI into your trading, you'll want to save this. How to build a performance review dashboard with Claude (step-by-step):

@DamiDefi this is real alpha already installed obsidian for myself, gonna try it out

EVERYONE HAS BEEN TALKING ABOUT AI SECOND BRAINS. BUT ALMOST EVERYONE IS BUILDING THEM THE WRONG WAY. Most people think an AI second brain is just dumping notes into a folder. It's not. The real advantage isn't storing more data. It's designing a system your AI actually knows how to navigate. Here's the 5-level framework that changes everything: Level 1: Build routing before intelligence. Give your AI clear instructions on where every type of information lives, so it stops asking you the same questions repeatedly. Level 2: Turn isolated files into connected knowledge. Organize notes into topic-based wikis that let AI traverse concepts instead of opening random documents. Level 3: Add semantic search only where it matters. Keyword search finds words. Semantic search finds meaning. But don't vectorize everything because some data still needs full-document context. Level 4: Map relationships, not just documents. Knowledge graphs let AI understand how people, projects, companies, and decisions connect instead of treating them as separate files. Level 5: Automate the brain, not the chaos. Continuously syncing everything sounds powerful until irrelevant data becomes permanent noise. Curate what enters your second brain. The biggest insight? Your second brain isn't a database. It's a retrieval system. The winners won't have the most information. They'll have AI that knows exactly where to look, in what order, and when to stop searching. That's the difference between an AI assistant and an AI operating system. Video cred: Nate Herk | AI Automation (Youtube)

@AnatoliKopadze watched this lecture the other day if you haven't seen it, you def gotta watch it

Google just dropped a 1-hour course on agentic engineering from scratch: 00:00 - Build your first AI agent 08:24 - Give your agent real memory (short, persistent, long) 28:34 - Agentic loops that run for hours on their own 40:04 - Build your own MCP (MCP VS API) 1:00:22 - Wire up multi-agent systems 72 minutes and you'll understand agents better than most people building them. Watch it today, then read the step by step guide for beginners on building loops below.

@papa_couch i think so too

@Granite0x smart solution👍

He wrote the #1 prompt-engineering guide on the internet. instead of keeping his LLM research private, he open-sourced it. Elvis Saravia, PhD. Founder of DAIRAI. Ex-Meta AI. Ex-Elastic. 'Prompt-Engineering-Guide' - the free guide 76K devs learned LLM prompting from. Zero-shot, few-shot, chain-of-thought, ReAct, RAG, AI Agents - all in one repo. 76,389 stars. MIT. → github.com/dair-ai/Prompt… bookmark it. This is how your Claude prompts go pro.

@0xMortyx that many stars got me too

@Granite0x damn, crazy amount of stars

@sairahul1 really sad to hear that got a ton done with fable 5

@RoundtableSpace could y'all have thought like a year ago that stuff like this would be in open source? personally, no

Anthropic has just published a free course on Loop Engineering If you use AI agents, bookmark it

@mikenevermiss saw this repo Archive made a really solid tool

AN ANTHROPIC ENGINEER JUST SHARED THE CLAUDE SETUP THAT MAKES ONE PERSON WORK LIKE AN ENTIRE TEAM

@cyrilXBT i don't use obsidian either and idk why been about time to start already

I GENUINELY DO NOT UNDERSTAND WHY EVERYONE ISN'T USING THIS YET. Andrej Karpathy, OpenAI co-founder, posted an idea that went massively viral. Stop using AI to write code. Use it to build a second brain instead. Point Claude Code at a folder. Drop in anything, an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. The whole setup. Install Obsidian Create a vault Open it in Claude Code Paste Karpathy's wiki idea and tell Claude to build it Claude makes three folders. raw for sources, wiki for its pages, a CLAUDE.md that runs it all Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up. You never start from a blank chat again. Full step by step guide below. Bookmark this. Follow @cyrilXBT

@eng_khairallah1 real alpha thanks for sharing this video

GOOGLE CEO SUNDAR PICHAI: "IF YOU DON'T LEARN HOW TO ORCHESTRATE AGENTS NOW, YOU'LL SPEND 2027 CATCHING UP TO PEOPLE WHO STARTED TODAY." 30 minutes on why the best engineers stopped writing code line by line and started orchestrating agents instead. Most people think building an agent requires an engineering degree. It doesn't. It requires one guide and one afternoon. Watch the interview. Then read the article below. One guide. One afternoon. That's all it takes.

@DamiDefi only a few hours left to use fable 5...

HERE IS HOW YOU CAN USE FABLE 5 BETTER THAN 99% OF PEOPLE The biggest advantage comes from knowing exactly when to use it and when to delegate. → Use Fable 5 for strategy, design, and high-stakes decisions. → Let cheaper models handle editing, formatting, and repetitive work. → Nail your first prompt: It saves both tokens and time. → Keep context small and start fresh chats after major tasks. → Always have another model review important outputs before shipping. This is one of the best AI workflow breakdowns I've seen. Bookmark this post, watch the full video this weekend, and you'll immediately build smarter AI workflows while spending less. Video cred: Jack Roberts (Youtube)

@sairahul1 fable 5 forever???? no way, gotta watch this video

SOMEONE JUST FOUND A WAY TO USE CLAUDE FABLE 5 FOREVER, EVEN AFTER ANTHROPIC LOCKS IT DOWN ON JULY 12TH. he used Opus 4.8 to extract the entire operating manual of Fable 5 in a single prompt. access to the best model is never guaranteed. it disappeared once already this year. but you can keep it forever. here's the trick: > Fable 5 has a "brain" — a complete set of thinking instructions baked into its weights > you can extract that brain into a single .md file in under 5 minutes > paste it into any Claude project and any model starts thinking like Fable 5 > Anthropic can rotate the model. they can't touch your local file. the prompt that extracts it. the exact project setup. the pressure test to verify it worked. all of it is in the article below ↓ do this today.

@cyrilXBT yeah most people make these kind of mistakes that's why i'm recommending everyone watch this video

MOST PEOPLE PROMPT CLAUDE THE SAME WAY THEY PROMPTED CHATGPT THREE YEARS AGO. Anthropic's own team does not. They published a 24 minute workshop, 40 techniques, on how they actually prompt it internally. I watched it expecting minor tips. Instead I found out the entire mental model I had been using was outdated. Free. No signup. Watch it, then read the article below. Follow @cyrilXBT

@rubenhassid thanks for putting everything in one place that's exactly what i was missing

Stop collecting 100 ridiculously long Claude guides. I've already mapped it for you. Here is how: 1. Go to Claude (desktop app). 2. Pay for the $20/month plan. I pay $100. Worth it. 3. Claude is 4 tools: Chat, Cowork, Code, Skills. 4. Most people never leave Chat. Big mistake. 5. My skill is free to download at how-to-ai.guide. 6. The download link is in the welcome email. 1. Chat → think out loud. Get an answer. Fast. ☑ Quick rewrite, fast question, brainstorm. ☑ Research mode: It sends agents to dig the web. ☑ Connect your Gmail. Ask questions to your inbox. ☑ Give it goals instead of simple tasks. ☑ The biggest trick: don't prompt better. End your prompt with "ask me questions first, using the AskUserQuestion tool." 2. Cowork → hand off the whole job. ☑ 5+ mini-Claudes plan, search & build. ☑ Use Skills + Projects. Instead of folders & files. ☑ Build it in Cowork, export to Google Drive. ☑ The money rule: never send a follow-up. Every "no, I meant..." makes Claude re-read the entire chat. Edit your original prompt instead. 3. Code → build software in plain English. ☑ This is what "vibecoding" actually is. ☑ Create an empty folder just for it. ☑ Turn on "bypass permissions" ☑ Connect Netlify + Supabase. Your site goes live. ☑ It's not for getting rich. It's for handing your dev team a clickable version so they stop guessing. 4. Skills → teach Claude once. Reuse forever. ☑ Any task you repeat weekly = a Skill. ☑ Claude recognizes the task & fires the Skill. ☑ Stuff it with your best posts, SOPs, or 30 PDFs. ☑ Skills save you money without burning tokens. ☑ Already in a great chat? Click the chat name → "make it a skill." Done. I collected my favorite Skills into one library. It's free in my welcome email: how-to-ai.guide Skill or Project? The 5-second test: ☑ Can you teach it to a person → Skill. ☑ Is it one client or campaign → Project. ☑ The real magic: your Skill, running inside a Project ♻️ Repost this to help others use Claude better.