Avid

this f**king dangerous someone figured out how to use claude fable 5 and GPT 5.6 together in chatgpt codex it took me only 5 minutes to set it up. here is how 1) run these in Codex -> codex plugin marketplace add Cjbuilds/Codex-Orchestration -> codex plugin add codex-orchestration@codex-orchestration 2) tag /Codex Orchestration and setup an executor model ( cheaper model) and advisor (Expensive model) 3) Paste the "Workflow Prompt" and then describe the task Save and Bookmark this no matter what it will be the most productive thing you do this week

@noisyb0y1 @rohit4verse Insane share

Stanford leaked for free a 60-minute AI course lecture that paid universities sell for $75,000: I sent this to my friend - 3 months later his AI product makes $60k a month: 00:10 - AI automates your entire life 23:52 - Claude cuts your 8-hour workday down to 20 min 49:34 - you don't need a degree to make $60k a month This 60-minute talk replaces a year of studying AI at Stanford for $90,000 a year. Watch it today, then read the full breakdown in the article below.

@leopardracer second brain is so good

the second brain enterprise team ran 100 companies through AI transformation and leaked exactly what worked: 00:03 - claude tailoring business assessments live instead of hardcoding them for every industry 12:11 - one prompt telling you exactly which two channels to focus on based on your real unit economics 44:52 - the 20% who become AI operators and end up running five people's jobs solo this conversation gives you for free what most consultants charge five figures to figure out over months watch it today, then see who in your team could be that 20%

this f**king dangerous someone figured out how to use claude fable 5 and GPT 5.6 together in chatgpt codex it took me only 5 minutes to set it up. here is how 1) run these in Codex -> codex plugin marketplace add Cjbuilds/Codex-Orchestration -> codex plugin add codex-orchestration@codex-orchestration 2) tag /Codex Orchestration and setup an executor model ( cheaper model) and advisor (Expensive model) 3) Paste the "Workflow Prompt" and then describe the task Save and Bookmark this no matter what it will be the most productive thing you do this week

Google pays AI engineers $450,000 a year to build AI models That same Google Engineer just dropped a 1-hour course on AI engineering from scratch: 00:00 - Build your first AI agent 08:24 - Make your AI Agent remember everything 28:34 - Agent Loops which make it work 100x 40:04 - Build your own MCP from Scratch 1:00:22 - Make 1000s of Agents work together 72 minutes is all it takes for you to understand AI Agents better than most developers who spend 6 months reading through X threads Save this and then read the article to understand how your Agent actually looks like on the inside

@zodchiii Nice article

@gippp69 This is so cool

THIS F**KING 7,300 STAR REPO TURNS CLAUDE FABLE 5, CODEX, AND CURSOR INTO ONE AI TEAM THAT KEEPS WORKING WHILE YOU SLEEP 00:01 he opens Omnigent, an open source layer that puts multiple coding agents inside one workflow while sandboxes and policies control exactly what they can touch. setup takes minutes. Fable acts as the supervisor, cheaper models handle execution, and premium tokens are reserved for decisions that actually need judgment. each task gets split across separate agents and git worktrees, then a fresh model reviews the final diff before anything can merge. a $5 daily cap, 150 line approval limit, automated signoff tests, and a 95% pass rate keep the whole team from running wild. bookmark this. one repo, four agents, and roughly 15 to 20% of the usual token cost.

@Menace_thakur this is awesome

Spent an amazing day at the OpenAI Build Hackathon. We couldn't make it to the first place, but I'm still really happy with how things turned out. We finished in the Top 10, securing Rank 7 among so many talented teams.

@RohOnChain thank for sharing this alpha brother

My friend applied to 200 tech jobs in two years. No MIT. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. A 4-hour course on mastering Claude Code. I watched it last night. Halfway through, I realized I've been using Claude Code completely wrong for a year. Bookmark this and read the article below. • 00:00 - Claude Code setup • 49:34 - building apps with Claude Code • 2:07:52 - prompting Claude Code • 2:46:16 - Claude Code for production

@noisyb0y1 this is so cool

I PASTED ONE PROMPT INTO CLAUDE - AND IT BUILT ME A FULL CLIENT ACQUISITION SYSTEM IN MINUTES no more agencies, no more sales team - one prompt and the system finds clients itself Claude analyzed the niche, found where clients hang out, wrote outreach scripts and built the funnel from zero what agencies charge $3,000/month to do manually - done automatically in one session the system runs 24/7, finds leads, qualifies them and passes only the ones ready to buy one prompt replaced an entire sales department - and costs $20/month instead of $3,000

@cgtwts W in the chat

We’re closer to AGI than most people realize.

@cgtwts lets go this is hilarious

@cgtwts this is awesome

@gippp69 This is high alpha Gipp lovely

SOMEONE GAVE CLAUDE FABLE 5 A CONTRACT, A $5 DAILY BUDGET, AND A MANAGER. THIS F**KING DANGEROUS SYSTEM CAN CLEAR A WEEK OF BACKLOG WHILE YOU SLEEP. 00:03 he opens Microsoft’s 4,900 star Agent Governance Toolkit, built for policy enforcement, isolated execution, identity controls, and protection against all 10 OWASP agentic risks. setup starts with 3 files. CONTRACT MD sets the limits, boundaries MD defines what the agent can touch, and signoff SH runs every test before anything ships. four roles split the shift. one model reads the logs, Fable picks the highest value task, another writes the code, and a fresh Fable reviews the final diff. a $5 cap stops runaway sessions, commits above 150 lines need approval, and autonomy unlocks only after 20 runs at a 95% pass rate. one failed run sends the agent back to probation. the repo adds the guardrails, but the contract is what turns Claude from a chatbot into an employee.

@rohit4verse This is so cool I love it

This guy reverse engineered a neural network the way you'd decompile software. Instead of treating LLM as a black box, he maps raw activations to human readable concepts, then edits them while the model runs. 0:00 - ChatGPT claims it forgot your phrase. It's lying, and you can prove it 12:47 - clamping neuron 1393 flips the model from trusting Wikipedia to doubting it 13:52 - the twist: that same neuron fires hardest on acronyms. One neuron, many jobs 15:54 - sparse auto-encoders unscramble the mess into concepts you can read 21:06 - he cranks the doubt feature to 500 and the model breaks down babbling Model debugging is turning into software engineering. This is the clearest 24 minutes on how and detailed breakdown in the article below:

@Pseudo_Sid26 Good post

This article isn't just an "AI skill" article. This is more like ML in AI. A skill/knowledge not everyone has. I have said this again and again, people who have ML basics and knowledge will have a higher edge over people in the industry who just know AI engineering. This article has topics like- > Auto-encoders > Sparse auto-encoders > Latent space > Hidden states > Representation learning > Interpretability A lot of these topics appear simple, and so has this article tried to be but is it actually this simple ? To understand an auto encoder - you need to understand the whole encoder-decoder architecture first, sparse auto encoders is obvio built on top of it which needs understanding of activation functions, back prop and what not. Interpretability is a topic which is still being researched so much, there are still good research papers coming out on this topic. To understand it fundamentally takes time. Attaching a thread explaining interpretability and autoencoders/SAE in simple intuitive terms ( I developed while learning - no AI bullshit, and some research paper references as well ) 🧵:

@AnatoliKopadze Nice one Anatoli

Meta CTO Andrew Bosworth: "If you skip learning to integrate AI, you'll fall behind people who didn't, we both know that." The people who adapt now won't be waiting for the ones who don't. 45 minutes of straight talk from the man running AI at Meta. Watch it, then read the guide below on the Claude features 99% of people never find.

@cyrilXBT W share

YOU CAN BUILD AN AI SECOND BRAIN IN 15 MINUTES. No coding experience. No $1000 course. Here is the entire setup. Step 1: Download Claude Desktop. Step 2: Download Obsidian. Step 3: Create a new vault and start dropping .MD files into it. Step 4: Tell Claude Code to connect to your vault using Karpathy's prompt: gist.github.com/karpathy/442a6… That is it. Your entire knowledge base becomes searchable, connectable, and queryable by the most powerful AI model on earth. Every note you have ever written. Every idea you have ever captured. Every resource you have ever saved. Claude reads all of it, finds connections you missed, and surfaces insights from your own thinking that you FORGOT you had. Most people use Claude as a search engine. The people building second brains use it as an INTELLIGENCE LAYER on top of everything they know. That gap is the gap between asking Google a question and having a research partner who has read everything you have ever written. Bookmark this. Build it tonight. Follow @cyrilXBT

@RuujSs good share RUUJ

@mjibly In the replies

@Av1dlive Workflow prompt