Noam Eppel

@surim0n @claudeai I just registered :) If you are around Toronto you may be interested in: luma.com/tpy7056f

🚨 Official @claudeai for Marketing & GTM Community Meetup When: April 20th @ 6pm. Where: Downtown Toronto 🇨🇦 This one's for the marketers, growth people, and GTM folks that are using AI in their workflows. Live demos. Real use cases. People showing what they've built with Claude. Whether you're already deep in it or just figuring out where AI fits into your marketing stack - this is the room to be in. Spots are limited. Sign up for demo's, volunteers and attendance in comments.

🚨

Running packages and AI Agents on your main OS is a security risk. These supply chain attacks have shown how easy it is for malicious packages or compromised dependencies to easily slip into your dev environment and execute code on your machine. Having a completely separate computer just for development work is ideal. For those who don't have a second computer, here is a very simple way on macOS to isolate your dev tools from your main operating system. Once setup, it only requires one command to run! It launches an Ubuntu environment with its own tools and worktree, isolated from your main filesystem. This reduces your attack surface so even if you download a malicious package, it should not impact the data on your main OS. 👇 Goal: With one command "claudebox" in your macOS terminal, launch a fresh Linux operating system, isolated filesystem, and separate Claude worktree every time using Ubuntu Multipass. 1. Install multipass cli on macOS: canonical.com/multipass/inst… 2. In your macOS terminal create a script named claudebox​.sh in your home directory. nano ~/claudebox.sh Copy the entire script below into a file. The script is a template so ensure you modify it to make any required customization (change the repo URL, add any additional npm packages you need etc). #!/bin/bash set -e NAME="claude-$(date +%s)" # Change the Github URL to the repo you want to clone REPO_URL="github.com/YOURORG/YOURRE…" REPO_DIR="YOURREPO" # Launch fresh Ubuntu VM multipass launch --name "$NAME" --cpus 2 --memory 4G --disk 10G # Install tools + run Claude inside VM. multipass exec "$NAME" -- bash -lc " set -e sudo apt update sudo apt install -y git curl gh ripgrep curl -fsSL deb.nodesource.com/setup_lts.x | sudo bash - # Add any additional packages you need to this list: sudo apt install -y nodejs sudo npm install -g pnpm sudo npm install -g vercel sudo npm install -g @anthropic -ai/claude-code # Clone your repo cd /home/ubuntu git clone \"$REPO_URL\" \"$REPO_DIR\" || true sudo chown -R ubuntu:ubuntu \"/home/ubuntu/$REPO_DIR\" " # Open interactive shell multipass shell "$NAME" # Run Claude in isolated worktree # (Run this manually inside the VM after entering the shell) # cd /home/ubuntu/YOURREPO # claude --worktree # The Ubuntu VMs will accumulate so you should manually delete them later. # Uncomment if you want to delete the Ubuntu OS automatically when you exit. # multipass delete $NAME 3. Make the script executable, create a "claudebox" shortcut (alias), and reload your shell so you can run it immediately chmod +x ~/claudebox.sh echo 'alias claudebox="~/claudebox.sh"' >> ~/.zshrc source ~/.zshrc Now you can open your macOS terminal and just type one command: claudebox You get an isolated Ubuntu environment with its own tools and worktree. Launch multiple Ubuntu environments at the same time. If anything goes sideways, you can delete the VM and your host machine stays clean. NOTE: This script may not be right for your specific environment and workflow. Ensure you modify the script as needed and test carefully before use.

The software supply chain has become the most critical and least-defended attack surface in modern software development. This week, someone hijacked one of the most popular packages on the internet and used it to install a backdoor on every machine that ran npm install. a16z's @MaikaThoughts, @zanelackey, and Joel de la Garza on how @SocketSecurity detected the Axios attack within 6 minutes, why AI is compressing software supply chain attack timelines, and why defenders have to move at machine speed to save the agents: a16z.news/p/et-tu-agent-…

I’m not sure you wrote any of your article. Emdash was released just a day ago. It is unsurprising the head of WordPress YouTube at Automattic is already criticizing it. WordPress has become stagnant with a highly insecure plugin ecosystem. I hope Emdash provides some healthy competition and is a wake up call. If WordPress is serious about their security, Emdash has just provided the blueprint for a secure plug-in architecture. Sandbox. Scoped. Audible. Cloudflare just did WordPress a huge favour.

@augustinbralley On a technical level yes. But that's not what I was trying to surface in my article.

👏 👏 👏 blog.cloudflare.com/emdash-wordpre…

Recent NPM supply chain attacks have shown how easy it is for malicious packages or compromised dependencies to easily slip into your dev environment and execute code on your machine. Running packages and AI Agents on your main OS is a security risk. Having a completely separate computer just for Dev work is ideal. For those who don't have a second computer, here is a very simple way on MacOS to isolate your Dev tools from your main operating system. Once setup, it only requires one command to run! It launches an Ubuntu environment with its own tools and worktree, isolated from your main filesystem. This reduces your attack surface so even if you download a malicious package, it should not impact the data on your main OS. 👇 Goal: With one command "claudebox" in your macOS terminal, launch a fresh Linux operating system, isolated filesystem, and separate Claude worktree every time using Ubuntu Multipass. 1. Install multipass on macOS: canonical.com/multipass/inst… 2. In your macOS terminal create a script named claudebox.sh in your home directory. nano ~/claudebox.sh Copy the entire script below into a file. The script is a template so ensure you modify it to make any required customization (change the repo URL, add any additional npm packages you need etc). #!/bin/bash set -e NAME="claude-$(date +%s)" # Change the Github URL to the repo you want to clone REPO_URL="github.com/YOURORG/YOURRE…" REPO_DIR="YOURREPO" # Launch fresh Ubuntu VM multipass launch --name "$NAME" --cpus 2 --memory 4G --disk 10G # Install tools + run Claude inside VM. multipass exec "$NAME" -- bash -lc " set -e sudo apt update sudo apt install -y git curl gh ripgrep curl -fsSL deb.nodesource.com/setup_lts.x | sudo bash - # Add any additional packages you need to this list: sudo apt install -y nodejs sudo npm install -g pnpm sudo npm install -g vercel sudo npm install -g @anthropic-ai/claude-code # Clone your repo cd /home/ubuntu git clone \"$REPO_URL\" \"$REPO_DIR\" || true sudo chown -R ubuntu:ubuntu \"/home/ubuntu/$REPO_DIR\" " # Open interactive shell multipass shell "$NAME" # Run Claude in isolated worktree # (Run this manually inside the VM after entering the shell) # cd /home/ubuntu/YOURREPO # claude --worktree # The Ubuntu VMs will accumulate so you should manually delete them later. # Uncomment if you want to delete the Ubuntu OS automatically when you exit. # multipass delete $NAME 3. Make the script executable, create a "claudebox" shortcut (alias), and reload your shell so you can run it immediately chmod +x ~/claudebox.sh echo 'alias claudebox="~/claudebox.sh"' >> ~/.zshrc source ~/.zshrc Now you can open your macOS terminal and just type one command: claudebox You get an isolated Ubuntu environment with its own tools and worktree. Launch multiple Ubuntu environments at the same time. If anything goes sideways, you can delete the VM and your host machine stays clean. NOTE: This script may not be right for your specific environment and workflow - ensure you modify the script as needed and test carefully before use. I hope this is useful! Would appreciate a repost for visibility to help it reach the right people.

GOAT.

Fitness, health, and physical discipline are becoming how people reclaim agency in a world that feels increasingly unreal. writing.tobyshorin.com/body-futurism/

Something fundamental has shifted in how software gets made, and I don't think most people have fully processed what it means yet. For most of computing history, software could only be created by experienced developers and was expensive to build, designed for the broadest possible audience, and distributed at scale because that was the only way to justify the cost of making it. You didn't get the tool that fit your life; you got the tool that fit everyone's life, more or less, and you learned to work around its edges and quirks and navigate around the bloat and dozens of features you don't use. That entire framework is collapsing, driven by AI models that can code as well as senior developers - and are improving exponentially. AI democratizes building software and now founders, operators, doctors, teachers, researchers are suddenly discovering they can build their own tools, shaped entirely around how they actually think and work. You describe what you want, clearly and specifically, and working software emerges from that description. What strikes me most about this shift is that it doesn't make software less valuable - it makes it far more so, because for the first time it can be genuinely personal. When AI frees you from having to write or review every line of code and manually battle obscure syntax errors, it allows people to focus on what really matters: building and creating solutions. It is the start of the ERA of Hyper-Personal Software. A system you built yourself, or had built to your exact specifications, that understands your particular workflow and reflects your actual priorities - that's something categorically different. Since software can now be developed quickly with minimal time and resources, some software can be transient, built to help plan a trip, organize a conference, track a hiring process, manage a research study, and then discarded. There are a lot of people who just want to be able to talk to an AI agent, describe the software they need but not worry about security, hosting, scalability, databases, backups, authentication, etc. I built ARI Software as a framework for hyper-personal software and a personal productivity workspace. It comes with dozens of built-in modules such as a task manager, fitness tracker, knowledge base for storing your notes, document repository, and many more. But the real magic is that it enables you to build your very own modules just by talking to an AI agent. Fully extendable. No coding required. It is not a SaaS - it is open source and gives you full data control. Install it on your computer or host it online so you have a secure, personal workspace available anywhere. The shift isn't just AI-generated code. It's AI-generated code built on strong foundations that give builders freedom without the brittleness that comes from working without guardrails. Software used to be built for the average user. Now it can be built by you for you. ARI Software launches later this month! Please give me a follow if you would like to hear more :) youtube.com/watch?v=mxxN4g…

Citadel Securities published this graph showing a strange phenomenon. Job postings for software engineers are actually seeing a massive spike. Classic example of the Jevons paradox. When AI makes coding cheaper, companies actually may need a lot more software engineers, not fewer. When software is cheaper to build, companies naturally want to build a lot more of it. Businesses are now putting software into industries and tools where it was simply too expensive before. --- Chart from citadelsecurities .com/news-and-insights/2026-global-intelligence-crisis/

Congrats on /voice mode! @bcherny Claude has the command-line flag --dangerously-skip-permissions Does Claude have an opposite flag such as --never-modify-files so a user can chat with Claude without concern it would change any files? Claude can enter /plan mode, but it is easy to accidentally exit plan mode. A more strict flag such as --never-modify-files would be useful when you want to research, explore, and interact with a codebase without any risk of it modifying files.

🎶 I've been using voice mode to write much of my CLI code this last week Can't wait to hear what you think.

We need a modern "10 Commandments" for responsible AI agents. Thou shall not commit private API keys to GitHub and pray nobody notices. GitHub notices. Everyone notices.

"We used to debate using tabs vs spaces in code we'd type out"

@heyandras You may like ARI.Software then. Launching in a few days

If I see open-source and self-hostable I press like. You should do it as well.

🚨 While running smaller AI models (MiniMax 2.5, Kimi 2.5 etc) locally with OpenClaw can save money, prompt injection resistance is not uniform across model tiers. Smaller/cheaper models are generally more susceptible to prompt injection and manipulation attacks. Recommendation: use the latest generation, best-tier model appropriate to the risk profile of the task. If you must use a smaller model, reduce blast radius (read-only tools, enable sandboxing for all sessions, minimal filesystem access, strict allowlists).

1. Less Words. 2. More Friends.

@photomatt @kavinbm Attached are two screenshots of the default WordPress Posts page. One is from late 2025. The other is from 8 years ago. They are almost identical. Stability or stagnation?

Yes, building on existing open source projects can be beneficial - when it actually makes sense to do so. Matt, take a look at this screenshot. This is what a typical person sees today when they log into their WordPress site: multiple alerts, plugin advertisements, security warnings, update notices.. Serious question: if you're building a new website today, why build it on WordPress in the age of AI? Matt sit down with a typical small business owner who runs a WordPress site. Ask them to add a YouTube video to a page. That's it. Watch what happens. Watch them log in, navigate the cluttered dashboard, click through layers of menus, search for the right page, wrestle with Gutenberg or Elementor, maybe they need to visit the plugins page to search and install a video plugin that actually works, insert the video, preview it, adjust it, preview it again and hope adding the video didn't break anything. Or you could show them they can open Claude Code and type, "Please add this YouTube video to the Contact page, full-width and add a short caption underneath the video." and have it implemented correctly in under a minute and be done. What are we actually gaining by preserving the clunky, slow WordPress dashboard? What value is this adding? At what point does it make more sense to replace stagnant legacy systems with new tools that genuinely work better for users? The WordPress investment in testing and hardening is real. But it is no longer the advantage it once was. AI has bent the development curve so significantly that accumulated time is less valuable than rapid feedback loops and continuous hardening.

I setup OpenClaw exactly 7 days ago. Since then here's what I've built. In 2025, this would've taken a team of 10-20 people 6-9 months and $1M+ in funding. 7 days. Just Me + OpenClaw + Claude Code. Building 12-15 hours a day. Total cost ~$600 (Tokens, Compute etc). PRODUCTS 1. Simple Notes: A full blown Apple Notes replacement with full sync working on all devices iOS, Mac, Web, Android. 2. Lumenote: A full blown Obsidian replacement with full sync working on all devices with slick UX (handling markdown better) + AI fully integrated to speak to my knowledge base. 3. CleoAI: OpenClaw but for normies built into Telegram. You just talk to it. No app needed. OC is too techincal for a normie referencing settings and md files all the time. So a version that my gf and siblings can use. No tech speak, gog bs etc. Architecture is TBD. OC has a hard coded system prompt that is tricky to override so likely I just re-build OC from scratch (with better security) or re-build all skills in a way that sound non-tech. WIP. Waiting for Apple to approve a new developer account to publish 1 & 2. Btw, all using Vercel, Railway, Supabase behind the scenes. AGENTS This has been unreal. I setup OpenClaw 7 days ago + Telegram and I did not know what to expect. In short, there are just no limits. Here's my current setup (evolving fast): 1. Sam (CoS): Sam is my new Chief of Staff. And calling him a CoS is a massive understatement. Here's all the things he's doing already: • Emails: Helped me triage and make sense of a 1000+ emails (has full access to my Google account). • Calendar: Drives my calendar and appointments • Bookings: My go to for booking restaurants. He uses my Chrome browser in a different profile to browse and book. • Shopping: Helped me shop for a few things. Research to filling my shopping cart online. He sent me a payment link to pay via Telegram through which I paid (I was walking at the time). • Groups: Sam is in 3 group chats with me and a few friends helping out with a few things. I don't think they know he's an agent (!). • Code & Build: Helps make quick fixes to all projects above and sometimes is better than Claude Code • Personal CRM: Built and maintains a 697-contact CRM from my Gmail + Calendar. Know who I talk to, when, and how often. • Optimizes Infrastructure: Security audits, gateway config, model routing optimization (Opus Orchestra), cost management. Sam has memory across all sessions and maintains daily notes. He also spins up 5+ sub-agents often automatically to get work done. I've given him tasks overnight only to realise he's done the in 30 mins. Sam also has his own email and his own phone number. I've plugged in ElevenLabs to give him a super voice. It's unreal. 2. Midas (Investor): Midas is my autonomous crypto trading guy. Calling him an agent is like calling a hedge fund manager a calculator. Here's what he's doing: • Portfolio Management: Managing a meaningful size portfolio with a 14-week DCA deployment strategy. • Trade Execution: Executes trades directly on exchanges. Sizes his own DCA tranches, handles currency conversions, places market and limit orders all with built-in risk guardrails. • Yield Farming: Autonomously stakes ETH and SOL on exchanges with custom trigger rules. Knows when to unstake for take-profit and when to restake on dips. • Risk Management: Tracks portfolio drift vs targets, flags overweight positions, adjusts DCA allocations to correct imbalances. E.g. automatically skipped BTC in Week 3 because it was 65% of portfolio (target 45%) and reallocated to underweight tokens instead. • Market Intelligence: Scans markets every 4 hours pulling from 8 live data sources. Calculates RSI, tracks on-chain metrics, monitors ETF flows to inform decision making. • Strategy: Operates under a locked strategy document that I've built with it's help, that governs every decision. Has its own trigger framework and won't deviate without approval. • Daily Briefs: Morning brief every day with prices, P&L, drift analysis, macro signals, and yield tracking. Weekly deep dives on Sundays with thesis reviews and watchlist scans. Midas has full exchange API access (trade, query, staking) but can never withdraw funds. He speaks in market language, celebrates wins, owns losses, and keeps me honest when I want to FOMO. 3. Ritam - ऋतम् (Physics Research): Ritam is my deep science research guy. He's focused on one mission -understanding gravity well enough to engineer it. Here's what he does: • Vedic-Modern Bridge: First, takes Vedic science seriously as physics. Treats the universe as one unified system from which matter, life, consciousness emerge. Looks for where ancient models make testable predictions. • Research & Paper Hunting: Searches arxiv, patents, journals, and obscure sources for bleeding-edge physics from EM universe theory, anti-gravity, torsion fields, scalar waves, and modified gravity theories. • Theory Synthesis: Cross-references across domains. For e.g. it connected ball lightning confinement to plasma physics to Gertsenshtein EM↔gravity coupling and proposed a hypothesis 🤯 • Engineering Oriented: Every theoretical insight gets pressure-tested with "so what can we build?" Equations and models are means to an end. The goal is technology for humankind. Ritam has full web search, paper access, browser automation, and compute tools. He speaks in physics, gets genuinely excited about breakthroughs, and won't sugarcoat when an idea doesn't hold up. 4. More Coming: There at least a dozen more agents WIP. I just spun a team of agents for Marketing & Distribution and I have no idea what to expect!

Comprehensive technical deep dive of OpenClaw's code - from foundational architecture, component orchestration, and system design. 👀 ari.software/openclaw-techn…

OpenAI: "GPT-5.3-Codex is our first model that was instrumental in creating itself. The Codex team used early versions to debug its own training, manage its own deployment, and diagnose test results and evaluations." When Boris Cherny, the creator of Claude Code, was asked how much of it was written by Claude, he replied, "All of it." AI is building itself. This is recursive self improvement in action. Each iteration strengthens the system that produces the next one. Wild. It's time to white pill yourself frens. There has never been a better time to build, launch, validate, and compete. The tools are stronger, the feedback loops are faster, and the barriers are lower. It's time to build.