In partnership with

Anthropic Does Not Stop

Yesterday, we discussed labs trying to "drain" Claude’s brain. Today, Anthropic gave you a way to take that brain to the beach.

Anthropic just dropped Claude Code v2.1.53, and the headline feature is a literal game-changer for anyone who hates being chained to a desk: /remote-control.

What Just Happened

Claude Code (the CLI) now supports a secure, mobile-friendly bridge. You fire up a massive refactor or a complex deployment on your workstation, run the command, and Claude generates a secure session URL.

You can now:

  • Monitor progress from your phone while you’re grabbing coffee.

  • Approve "Plan Mode" steps via a mobile-optimized UI.

  • Inject new goals into a running agent session without touching your keyboard.

Current Vibe After Anthropic Ships A Gazillion Things In a Couple Weeks

ARTIFICIAL INTELLIGENCE
🧠 The Brain Upgrade: What’s Actually Happening?

If you think this is just a "mobile app," you’re missing the bigger picture. Anthropic just unified their model stack (Claude 4.6) with their coding engine (Claude Code v2.1.53).

Here is the breakdown of the new "Agentic" capabilities:

1. The "Hydra" Sub-Agents

Claude no longer works alone. When you give it a big task (like "Refactor my entire API"), the main agent spawns Sub-Agents.

  • One agent focuses on the Database.

  • One agent writes the unit tests.

  • One agent handles the documentation. They run in parallel, meaning complex work that used to take 20 minutes now finishes in 3.

2. Adaptive "Thinking" Modes

You’ll notice new commands like ultrathink. This isn't just a marketing term. Claude 4.6 uses dynamic reasoning scaling.

  • Small task? It barely "thinks," saving you tokens.

  • Complex architectural bug? It scales its internal "hidden" chain-of-thought to reason through 10+ files at once before it even types a single character.

3. The 1 Million Token "Memory"

Claude Sonnet 4.6 just hit a 1M Token Context Window in beta. For context: you can now drop your entire codebase, your API docs, and 50 research papers into a single session. It no longer "forgets" what you said at the beginning of the chat.

4. The "Remote Control" Bridge

The /remote-control command isn't just a screen share. It’s a secure tunnel to the Claude Code VM. It allows you to:

  • Interrupt & Steer: See Claude making a mistake on your phone and type "Stop, use the other library" in real-time.

  • Accept/Reject Edits: Swipe right to approve a code change from your couch.

What’s The HYPE?
🛡️ The "Auto-Pilot" Risk Check

When you give an AI "Remote Control," the first thing people worry about is it accidentally deleting their files while they aren’t looking.

The "Dangerously Skip" Mode The update includes a new setting called --dangerously-skip-permissions. Usually, Claude stops and asks, "Can I run this command?" but in Remote Mode, you can flip a switch to let it run on Auto-Pilot.

  • The Reality: Most pros are running this in a "sandbox" (a safe, isolated digital box). If you’re running it on your main computer while you're at lunch, you're essentially letting a robot drive your car while you're in the backseat. It’s incredibly fast, but it requires you to trust your setup.

    The Control of AI and Safety deems more importance as we progress in development

    shared.image.missing_image

Check Out A Free AI BROWSER!

World’s First Safe AI-Native Browser

AI should work for you, not the other way around. Yet most AI tools still make you do the work first—explaining context, rewriting prompts, and starting over again and again.

Norton Neo is different. It is the world’s first safe AI-native browser, built to understand what you’re doing as you browse, search, and work—so you don’t lose value to endless prompting. You can prompt Neo when you want, but you don’t have to over-explain—Neo already has the context.

Why Neo is different

  • Context-aware AI that reduces prompting

  • Privacy and security built into the browser

  • Configurable memory — you control what’s remembered

As AI gets more powerful, Neo is built to make it useful, trustworthy, and friction-light.

Try Norton Neo Now

AI Assistant
🎮 The Final Takeaway: Coding as a Lifestyle?

If you’re a builder, the "Remote Control" isn't a toy—it’s a management shift. We are officially entering the "Post-Laptop" era. If you can steer a $200B AI model from your phone while waiting for a flight, the old rules of "working 9-to-5 at a desk" are effectively dead.

The question for the week: Are you ready to stop being the one who types the code and start being the one who orchestrates the results?

Imagine If You Told A Software Engineer in 2013, that you could prompt an imaginary brain from your phone to code for you?

AI Market Takeover
🤖 Notion 3.3: Hire Your First "Digital Employee"

While Anthropic gave Claude "hands," Notion just gave it an office. The 3.3 update launches Custom Agents—autonomous teammates that work 24/7 without you ever typing a prompt.

Notion Embraces AI

What’s the actual "New" part?

Notion AI is no longer a chatbot; it’s a workforce. You give it a job description and a trigger, and it runs while you sleep.

  • The Support Hero: It scans Slack, Email, and Calendar to answer repeat team questions (like "How do I book travel?") so you don't have to.

    Create AI Agents With Notion

    shared.image.missing_image

  • The Triage Agent: It watches your inbox, turns requests into tasks, and routes them to the right owner with >95% accuracy.

  • The Ghostwriter: It monitors project progress and automatically drafts your Friday standups, weekly recaps, or monthly OKR reports.

Notion AI Monitors Your Projects and provides summaries

  • The Tool Connector: Through MCP, your agents now "talk" to Slack, Figma, Linear, and HubSpot. It can turn a FigJam board into a Notion doc automatically.

    Connectors Within Notion Via Its MCP Integration

    shared.image.missing_image

Pick Your Brain 🧠

This is the pro move: You can toggle the model. Want Claude 4.6 for a nuanced status report but Gemini 3 for data-heavy task routing? You can now swap the "AI brain" based on the specific job.

The Big Picture Takeaway

We are officially moving from the "SaaS era" (software you use) to the "Agent era" (software that works for you).

Between Claude’s Remote Control and Notion’s Autonomous Agents, your job description is changing. You aren't the one doing the "busy work" anymore—you are the Orchestrator. Are you ready to stop typing and start supervising?

Stay building.

Check Out Our Latest YouTube Video

If you made it here - We don’t usually do this but reply to this email, with what you thought about this newsletter - WE LOVE HONEST OPINIONS!

Recommended for you