Codez

@0xRafy Wow. New session with Boris. Really amazing watch bro. Thanks for the share

Anthropic and Boris Cherny just dropped a full session on how Claude Code is replacing traditional engineering: • 00:00 - how Boris went from 5% to 100% AI-written code and deleted his IDE • 05:22 - how Boris runs 5 Claude Codes in parallel • 07:21 - Claude for people who never opened a terminal - CoWork • 38:32 - how to make Claude 10x more productive with skills • 49:00 - code modernization demo - COBOL to Java in minutes this 1-hour watch will replace 10 paid courses on Claude Code. Watch it today, then read the article below on how to build efficient agentic loops from scratch

@Av1dlive wow, this is top tier course Avid ! Thx for the share bro

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

NVIDIA engineer: "my job is two things. I build agents, and I babysit agents. 3 moments changed everything for me: • ChatGPT - when my parents finally got it. • Reasoning models - when model first high-fived itself. • January '26 - agents started running for hours on their own" in this 1‑hour talk, Nvidia engineers reveal how to build agents that can run for hours from scratch. Watch the talk, then save the playbook below.

@LyckyOus agree on this mate

@0xCodez ngl, self correction is key to scaling these ai models ser

@itsthedonhashim Babysitting agents is parenting, except the kid can fork processes and trade.

@0xCodez @0xCodez honestly, babysitting agents sounds like parenting on another level 😂

@0xFramez When “building agents and babysitting agents” is the job description, you know the future of software is orchestration, not just code.

@0xCodez Building agents and babysitting agents becoming the whole job description says a lot about where things are headed

@0xSlyth Babysitting is where the real engineering shows up - everything else is a demo.

@0xCodez babysitting is the real engineering

@MyWestLord Damn, what a wild setup here - real legendary structure. Thx for the share, bro.

Steph Ango, the CEO of Obsidian, and Claude Code just built the most powerful second brain method on earth, and the full system is INSIDE. While everyone was bolting “Ask AI” buttons onto note apps, Ango (kepano on GitHub) went the opposite way. The problem he saw was simple: Claude Code writes plain markdown and nothing else, so it doesn’t know wikilinks, callouts, Bases or Canvas, and pointed at your vault it fills your notes with broken links. So the CEO fixed it himself by shipping 5 skill files that teach Claude to write Obsidian’s native language: clean wikilinks and frontmatter, database views inside plain text, spatial maps on Canvas, full vault control from the terminal, and a stripper that turns any web page into clean markdown before saving. 41,500 developers starred them. Setup is one clone of his repo into your vault, plus a CLAUDEmd at the root with your folder structure and 3-4 rules that Claude reads first in every session. From there, 3 operations run everything: Ingest takes an article or PDF, splits it into atomic pages and updates 5-15 existing notes per pass, Query answers any question from your own notes while citing your own pages, and Lint sweeps the vault weekly to kill broken links, orphan pages and contradictions. No RAG, no vector database, no embeddings, just plain markdown that an agent reads directly, the same pattern Karpathy gist validated with 14,000 stars in 7 days. And here’s the detail everyone misses: Ango has run his own vault this way for 6 years with almost no folders, because linking beats filing. A meeting note links to a project, a person and an idea at once, while in a folder it lives in 1 place. He built Obsidian on “file over app”, the idea that apps die and plain text doesn’t, and then agents arrived and plain text turned out to be the one format they read natively. Every note app is now racing to add AI, yet the winner spent 6 years refusing to lock your files. He didn’t add AI to the app. He taught AI to speak its language.

@0xLoopz Thanks, Loopz! By the way, are you building long‑running agents yourself?

@0xCodez New banger format from Codez!

@AIAppsAPI Babysitting is the half of agent work nobody puts on the slide.

@0xCodez Babysitting is the honest half of the job description and almost nobody puts it on the slide. The ratio only improves when the agent has a narrow role and an output you can check in seconds. Broad agent, vague output, and you are not supervising, you are just reading.

@gippp69 Damn, this is truly an alpha setup - I’ll try to run the same business myself.

A DEVELOPER CONNECTED CLAUDE TO REVIT AND TURNED ONE LAPTOP INTO A $15,000 AI ARCHITECTURE STUDIO 00:04 the AI starts building the house directly inside Revit, creating walls, floors, rooms, and the first 3D model from one text instruction. traditional firms charge $15,000 to $80,000 for a full project, while concept packages alone can sell for $3,000 to $15,000 before construction drawings begin. one person can now deliver 6 to 8 renders, a floor plan, and a client walkthrough in 3 to 5 days using Claude Code, Revit, Midjourney, and automated workflows. at 4 projects a month, a lean studio could generate $16,000 to $32,000 while spending under $200 on software, then partner with a licensed architect for stamped plans. bookmark this before the next architecture firm starts with one laptop, one prompt, and one client brief.

@rewind02 It’s not “build agents” - it’s “build agents you’re willing to delegate to.” Trust is the actual product.

@0xCodez the real role is building agents you can trust

@gippp69 You’re basically pointing at the moment where “agent frameworks” stop being glorified cron jobs with human chaperones and start behaving like actual delegated operators.

@0xCodez the distinction between building and babysitting agents really highlights how autonomy is only just now crossing a critical threshold

@0xMortyx Amazing watch, bro! Real alpha dropped here.

Jeffrey Litt's: "make your agent write you a quiz before you ship." Your AI agent just landed a 50,000-line PR. You approved it. You understood maybe 12% of it. You now have massive cognitive debt. 90% of "move fast with AI" advice skips the part where you stop being able to think creatively about your own project. You can't send code for review until you pass it. Watch the full talk. It changes how you think about AI-assisted engineering.

@AnatoliKopadze The Meta CTO is so right in this talk. If you don’t integrate AI, you’ve already lost!

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.

@0xClodex Wow bro, such a great guide on building LLMs. Anthropic pays 750k for engineers doing this - you dropped the pipeline for free.

Higgsfield crossed $500M annual run rate, 14 months after launch. We're growing 30% month over month, and last week we passed $2M a day in credit card billings. The bigger we get, the more we can invest in things that matter beyond our business metrics:

@0xCodez On it to burn tokens broskiii ty for sharinggg

Google just launched a 1-hour course on agentic engineering from scratch: • 00:00 – How to deploy your first AI agent • 22:10 – Build agent memory (short, persistent, long) • 42:18 - Advanced AI agent design patterns • 50:18 - How to build MCP (MCP vs. API) • 01:10:40 - Agentic loops, long-running AI agents This 1-hour video will replace 10 paid courses on agentic engineering. Watch it today, then read how to build a self-improving agentic system in the article below.

@0xRafy Wow fresh course on Fable5 by Anthropic. Real chad !

Anthropic just dropped a full guide on how to actually use Fable 5: • 00:00 - Fable 5 - what the new models can do • 18:03 - how to build Managed Agents with Fable 5 • 28:01 - next-level developer experience • 41:42 - autonomous agents with Fable 5 • 1:34:00 - run agents without burning money This 2-hour watch will replace 10 paid courses on building agents. Watch it today, then read the article below on how to build self-improving agents with Fable 5