bwo

[CyrilXBT @cyrilXBT]

THE CREATOR OF OBSIDIAN JUST TURNED YOUR NOTE VAULT INTO AN AI AGENT.

Not a plugin.

Not an integration.

A full agent skills system that teaches Claude Code, Codex, and OpenCode to READ, WRITE, and REASON inside your Obsidian vault like a power user.

27,000 GitHub stars in days.

Here is what shipped at launch:

obsidian-markdown — wikilinks, embeds, callouts, properties, the full Obsidian flavor Claude now understands natively.

obsidian-bases — Claude can create .base files with views, filters, formulas, and summaries.

json-canvas — Claude builds .canvas files with nodes, edges, groups, and connections.

obsidian-cli — Claude controls your vault, develops plugins and themes directly from the terminal.

defuddle — strips web pages into clean Markdown so you stop burning tokens on clutter.

Install the whole thing in one line:

npx skills add https://t.co/mHDEvCNOIC

Then connect it to Claude Code, Codex, or OpenCode.

That is it.

Your second brain now has an agent inside it that understands how Obsidian actually works.

Not a generic AI that pastes text into files.

An agent that knows what a wikilink is. What a callout is. What a canvas is.

Built on the open Agent Skills spec. MIT license. Free forever.

The gap between people using Obsidian as a note app and people using it as an AI operating system just got wider.

Bookmark this before you open your vault today.

Follow @cyrilXBT for every build that changes how Obsidian and Claude work together.

[Anatoli Kopadze @AnatoliKopadze]

Godfather of AI: "If you sleep well tonight, you may not have understood this lecture."

This 47-minute lecture is the best thing I saw about AI in the last few months.

It will definitely help you understand how it actually works and where it's going.

Geoffrey Hinton built the neural networks behind every AI alive, then quit Google to warn the world about it.

The part nobody wanted to hear:

> AI is already developing abilities its creators didn't intend
> in most cognitive tasks it's already ahead of us
> the question is no longer if it surpasses us but when
> the only decision left is which side of that line you're on

Right now the average person opens Claude, types something, gets an answer, closes the tab.

They think they're using AI. they're using maybe 10% of it.

I went through his entire lecture, then mapped everything he described to what Claude can actually do today.

17 Claude features most people will never find on their own.

Full breakdown in the post below.

[Microsoft Learn @MicrosoftLearn]

We’re introducing a new GitHub Certified: Agentic AI Developer (GH-600).
As AI agents become part of modern development workflows, this role-based certification focuses on how developers and teams operate, supervise, and integrate agents across the SDLC.

If you’re already working with tools like GitHub Copilot or exploring agent-driven workflows, we’d love your input.

Learn more and get involved. https://t.co/ruiYtlsYnj

[CyrilXBT @cyrilXBT]

GITHUB JUST CREATED AN OFFICIAL CERTIFICATION FOR THE MOST IN-DEMAND DEVELOPER ROLE OF 2026.

It is called Agentic AI Developer.

GH-600.

And it is the first formal signal that running AI agent teams is now a recognized engineering discipline with a credential behind it.

Not a prompt engineer.

Not a vibe coder.

An Agentic AI Developer.

The person who operates, supervises, and integrates AI agents across the entire software development lifecycle.

The person who knows where agents fail in production.

The person who understands how to build autonomous workflows that do not introduce catastrophic failure modes into CI/CD pipelines.

The person every engineering team is going to need and almost none of them have right now.

GitHub certifying this role changes the hiring conversation permanently.

Before GH-600: "Do you work with AI agents?" is an interview question with no standard answer.

After GH-600: the credential tells the hiring manager exactly what you know and what you can do before the interview starts.

The engineers who get certified in the first wave of GH-600 will have a credential for a role that has more demand than supply for the next 3 to 5 years.

The engineers who wait until it is mainstream will be competing with everyone who moved first.

If you are already working with GitHub Copilot or building agent-driven workflows you are already doing this job.

GH-600 is how you prove it.

Bookmark this.

Follow @cyrilXBT for every AI certification worth your time the moment it drops.

[Himanshu Kumar @codewithimanshu]

Claude is now controlling TradingView live from my terminal.

Switching symbols. Writing Pine Script. Batch scanning futures. Replay trading. Drawing levels.

All autonomous. Zero clicks.

Still has rough edges but the vision is crystal clear.

I told it:

Find me every BTC futures contract with RSI below 30 and volume spike above 200%.

14 seconds later:

→ 6 contracts identified
→ Charts loaded
→ Support levels drawn
→ Pine Script backtests running
→ Entry zones marked

Didn't touch the mouse once.

Then I said:

Replay last week. Show me where your system would have entered.

It switched to replay mode. Scrolled through price action. Marked every edge. Calculated P&L in real-time.

$4,780 theoretical profit from 9 trades.

83% win rate.

Now it writes custom Pine indicators on command:

Build me a momentum oscillator that tracks whale wallet activity correlated with price.

40 seconds. Script deployed. Indicator live on chart.

Most traders are still clicking through 50 charts manually.

Claude scans 200+ in under a minute.

Finds the setups. Draws the levels. Backtests the edge. All while you watch.

This is not about replacing your strategy.

It's about executing it 100x faster.

You only need Claude + laptop + 1 hour/day.

Giving This Free for 24 hours. To get it:

1. Comment the word CLAUDE
2. Like and Retweet this post
3. Follow me @codewithimanshu (so i can DM you)

Save this post. Deploy this setup this weekend. Start testing. Scale on evidence.

[Coin Bureau @coinbureau]

🚨 OG YOUTUBER PEWDIEPIE JUST LAUNCHED A FREE, OPEN-SOURCE AI RIVAL TO CHATGPT AND CLAUDE

While ChatGPT and Claude charge users for premium features, PewDiePie’s new AI workspace, Odysseus, is FREE.

In his own words, "NO tracking, NO subscriptions, and can be run on your OWN computer."

Odysseus is essentially “Claude and ChatGPT’s web UI, but SELF-hosted”, allowing users to run local AI models or use APIs while keeping control of their own data.

Odysseus includes:

- An AI agent that can find, create, edit and run files
- Memory that learns from past conversations
- Deep research with follow-up chat
- An email client that flags urgent messages and drafts replies
- A document editor for writing, formatting and fact-checking
- Calendar, to-do notes and search tools
- An image editor
- “Cookbook,” which scans hardware, recommends local models and helps users run them
- Mobile support

Its BIGGEST selling point is privacy and control.

“All your data is yours, as it should be.”

He also made a firm commitment on pricing:

“This project will never cost any money.”

The launch comes just days after PewDiePie announced he was ENDING his vlogs.

Retirement arc is wild.

[Noisy @noisyb0y1]

THIS CHINESE DEVELOPER VISUALIZED WHAT 300 KIMI K2.6 AGENTS LOOK LIKE IN ACTION - AND IT LOOKS EXACTLY LIKE A BRAIN WORKING FOR YOU

every line on screen is a connection firing in real time - hundreds of neurons across multiple layers, activations lighting up, signals passing through the network simultaneously in both directions

this is not a diagram and not a concept - this is the actual mechanics of what happens inside the model every time it processes your request

now multiply that by 300 parallel agents running 4,000 coordinated steps at the same time - while you drink coffee the entire system fires neurons and does the work for you

a team paying $62,000/month on Claude Opus cut their bill to $129 by switching to Kimi K2.6 as the execution layer - Opus plans, Kimi executes, $54,000/month stays in the business

what looks like fire on screen is your new employee who never sleeps, never asks for a raise and never goes on vacation

most people pay for subscriptions that forget everything tomorrow - he built a system that works and compounds while he sleeps

[Min Choi @minchoi]

AI is starting to build AI.

Anthropic just published one of the clearest signals yet.

Claude now writes 80%+ of Anthropic's production code.

Their engineers are merging 8x more code per day than in 2024.

That sounds like a productivity stat.

It' actually much bigger.

For most of AI history, humans did the whole loop:

- write code
- run experiments
- debug systems
- interpret results
- decide what to try next

Now Claude is taking over more of that loop.

At Anthropic, Claude can already:
→ write and edit code
→ run code
→ delegate work to agents
→ debug incidents
→ optimize experiments
→ review code before merge
→ catch bugs humans missed

One example was insane:

Claude shipped 800+ fixes that reduced a class of API errors by 1,000x.

The engineer said a human would have taken 4 years.

Claude did it in April.

The scary part is not that Claude writes code.

The scary part is that Claude is getting better at the work around the code:
> figuring out what went wrong
> testing fixes
> choosing next steps
> running experiments
> checking its own outputs

Anthropic says Claude went from about 3x speedup on one internal optimization task in 2025 to about 52x with Mythos Preview in 2026.

That is not normal tool improvement.

That is compounding.

The current human advantage is still taste and judgment:

What problem should we solve?
Which result matters?
Which direction is worth pursuing?
When should we stop?

But the "doing" part is getting automated fast.

This is the real shift:

Humans used to build AI.

Now humans increasingly steer agents that build AI.

And if that loop closes completely, you get recursive self-improvement:

AI systems designing, testing, and improving their own successors.

Anthropic says we are not there yet.

But they also say institutions are not ready if it comes sooner than expected.

The AI race is no longer just about better chatbots.

It's about who can build the fastest machine for improving intelligence itself.

[Coin Bureau @coinbureau]

🩸JUST IN: Over $635 BILLION WIPED OUT from the crypto market in less than a month.

+$500M in crypto liquidations hit in the last 1hr, long positions accounting for $450M.

[Indu Tripathi @InduTripat82427]

🚨 THIS GUY TOLD CLAUDE TO "BUILD GTA 7 USING JAVASCRIPT. MAKE NO MISTAKES."

One prompt later, Claude generated a fully playable open-world driving game.

🏎️ Real driving physics, drifting, car theft, pedestrians, police chases, radio stations, and even on-foot gameplay.

Everything runs directly in the browser.

The craziest part? It used only ~11% of his weekly Claude Max 5x usage. 🤯

[FarhanX_AI @FarhanBuildsAI]

🚨I SPENT 6 HOURS LAST WEEK DELETING MY DIGITAL FOOTPRINT WITH CLAUDE.

Result: 47 data broker listings removed. 12 dead accounts deleted. 3 search results buried.

Here's exactly how I did it, step by step. 🧵

[Elon Musk @elonmusk]

This provides some sense of scale

[bwo @nomadic_coder]

@RealChainGames

[Chain Games 🎮 @RealChainGames]

It's Dill or Die... 🥒

Coming 🔜

[Vikas gupta @vicky_grok]

The engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work

I've seen $300 courses that don't cover what he shows in the first 10 minutes

CLAUDE.md files, memory shortcuts, parallel sessions, prompting patterns

all in one video and completely free works whether you're a developer, a beginner, or someone who's been using Claude for months.

[ClaudeDevs @ClaudeDevs]

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal.

Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell.

The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

[bwo @nomadic_coder]

@RealChainGames So excited to play with you guys on multiplayer

[Nainsi Dwivedi @NainsiDwiv50980]

How to Learn Claude in 12 Days

(This will save you 2+ hours every day)

Most people use Claude like a chatbot.

Ask a question. Get an answer. Repeat.

Big mistake.

Claude is becoming an operating system for knowledge work.

Here's a 12-day roadmap based on real Claude workflows:

☀️ DAY 1: Build CLI Tools

Goal: Turn ideas into working tools.

→ Open Claude Code
→ Describe a tool in plain English
→ Let Claude generate and run it

No frameworks. No boilerplate. Just describe → build.

☀️ DAY 2: Create an MCP Server

Goal: Give Claude new capabilities.

→ Pick a tool or API you use often
→ Define endpoints and authentication
→ Let Claude generate the server

Now Claude can interact with your systems directly.

☀️ DAY 3: Build a Personal RAG

Goal: Make Claude remember your knowledge.

→ Upload notes, docs, and PDFs
→ Connect Google Drive, Notion, or Gmail
→ Ask questions across everything

Your second brain becomes searchable.

☀️ DAY 4: Understand Any Codebase

Goal: Learn unfamiliar code fast.

→ Drop in a GitHub repo
→ Ask for architecture breakdowns
→ Follow guided walkthroughs

Hours of reading become minutes.

☀️ DAY 5: Practice Interviews

Goal: Improve faster than studying alone.

→ Pick a role
→ Choose an interview type
→ Let Claude act as interviewer

Get feedback after every answer.

☀️ DAY 6: Automate the Browser

Goal: Stop doing repetitive web tasks.

→ Tell Claude what you need
→ Let it navigate websites
→ Complete tasks automatically

Research becomes delegation.

☀️ DAY 7: Tailor Every Resume

Goal: Apply smarter.

→ Paste a job description
→ Upload your resume
→ Ask Claude to optimize for ATS

Customized applications in minutes.

☀️ DAY 8: Schedule Cloud Routines

Goal: Work while you sleep.

→ Create recurring tasks
→ Schedule reports or research
→ Wake up to completed work

Productivity without active effort.

☀️ DAY 9: Design Faster

Goal: Go from idea to visual.

→ Describe a landing page
→ Describe a pitch deck
→ Let Claude generate drafts

Blank-page syndrome disappears.

☀️ DAY 10: Run Multi-Agent Reviews

Goal: Get multiple perspectives.

→ Assign different review roles
→ Let agents inspect code independently
→ Compare recommendations

One review becomes many.

☀️ DAY 11: Use Auto Mode

Goal: Delegate entire workflows.

→ Give Claude a specification
→ Let it plan, code, test, and review
→ Ship end-to-end

You manage outcomes, not steps.

☀️ DAY 12: Build Custom Skills

Goal: Create reusable expertise.

→ Save recurring workflows
→ Turn prompts into commands
→ Reuse them forever

Your best workflows become one-click actions.

Most people use Claude for answers.

Power users use Claude for systems.

The difference isn't intelligence.

It's setup.

Do this instead of scrolling:

→ Save this post
→ Start Day 1 today (10 minutes)
→ Complete one day at a time
→ Come back in 12 days

You'll never use AI the same way again. 🚀