Matthew

@AnthropicAI @claudeai please don’t use my context window for upsells

Self-hosting a NixOS VM on a Proxmox host which hosts a dozen homelab services from the *arr stack to grafana to macOS VMs. All infrastructure is declared with Terraform and Ansible. I reach into the homelab VLANs with @Tailscale and have Claude Code running around the clock

@bcherny @benswerd @bcherny I’ve been dealing with this bug for 6 weeks. Can you give us a rundown on why this was happening?

@benswerd This was a weird one, and is a two-part fix. First part is out now (update to the latest). Part two has landed and is going out in Monday’s release. To unblock yourself, /exit then claude -c

What did I do to my claude code

Spent last night grepping xAI's new Grok Build CLI! Thankfully, every system prompt is a plain string constant! Build includes subagents, memory consolidation, plan mode, loop detection. Happy to see the progress @xai granda.org/en/2026/05/15/…

@GergelyOrosz Definitely up next will be package registries (npm, PyPI, Docker Hub). Agents iterate, retry, and re-pull aggressively, and ephemeral sandboxes amplify it.

We now know AI agents broke a lot of past assumptions at. GitHub on expected service load + growth. What other services / domains are next where load could/should surge thanks to more AI agents used to do stuff?

@BrendanCarrFCC @NASAAdmin lil mayo ❤️

NASA astronauts will soon fly with the latest smartphones, beginning with Crew-12 and Artemis II. We are giving our crews the tools to capture special moments for their families and share inspiring images and video with the world. Just as important, we challenged long-standing processes and qualified modern hardware for spaceflight on an expedited timeline. That operational urgency will serve NASA well as we pursue the highest-value science and research in orbit and on the lunar surface. This is a small step in the right direction.

Built a spacecraft computer simulator from scratch! Bare-metal C on ARM Cortex-M3, FreeRTOS task scheduling, and NASA's delay-tolerant networking stack, all running in QEMU and Docker. No hardware required. granda.org/en/2026/03/30/…

@feross @amasad doesn't seem realistic to expect people to review their code when more and more of it is being generated blindly.. seems like we need good containerization defaults for dev work across the industry.

Yes, AI is playing a role in two ways: 1.Far more code is being written (1.5-2x by some estimates) and far more people are vibe coding without reviewing what their agents install. Every unreviewed dependency is an attack surface. 2.Attackers have woken up. We saw the first NPM worm last year. The recent TeamPCP attacks (against Trivy and LiteLLM) have stolen a massive number of credentials that most teams haven’t rotated yet. We’ll be dealing with the long tail of these compromises for 6-12 months. Not that developers were good at reviewing dependencies before. But AI has mass-produced the exact behavior attackers exploit.

🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages. The latest axios@1.14.1 now pulls in plain-crypto-js@4.2.1, a package that did not exist before today. This is a live compromise. This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now. Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that: • Deobfuscates embedded payloads and operational strings at runtime • Dynamically loads fs, os, and execSync to evade static analysis • Executes decoded shell commands • Stages and copies payload files into OS temp and Windows ProgramData directories • Deletes and renames artifacts post-execution to destroy forensic evidence If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade.

@swyx @dillon_mulroy @badlogicgames know how you can edit previous messages? Think about if you could edit any unit of the chat. Reverting a tool call e.g.

@dillon_mulroy explain the context mgmts thing more? also can u explain the webfetch websearch thing cc @badlogicgames

thoughts after day 1 of using pi full time - less is more - i don't miss subagents like i thought i would - /tree is an insanely good context management primitive (and partially why i havent reached for subagents yet) - based only on vibes, i think having a minimum system prompt is improving code quality - telling pi to copy opencodes webfetch and websearch tools was a good play

I added an agent to my CI pipeline that screenshots every UI state across three viewports on every PR push. Zero manual testing. Here's how it works granda.org/en/2026/02/06/…

@Scobleizer @digijordan What would you recommend reading @Scobleizer

@digijordan It is true. And I study Silicon Valley robotics all day long.

Tesla Optimus Gen 3 is coming out in a few months. Million of them per year to start. Musk is ending two models of Tesla so he can make more robots. People don’t realize what’s about to happen…

@FujiExpo Pls document your process

iOS 1.0 "Alpine" (1A420) Complete iTunes Restore on Production iPhone 2G

My blog links showed up as plain text on Twitter. No preview image. Just a naked URL. 14 minutes with Claude → every post now gets an OG image automatically. Playwright screenshots the post. GitHub Actions commits the image. Zero manual work. granda.org/en/2026/01/10/…

@Anthropic granda.org/en/2026/01/09/…

Setup is 5 lines of JSON: { "mcpServers": { "playwright": { "command": "npx", "args": ["@anthropic-ai/mcp-server-playwright", "--headless"] } } } GitHub issues become living test reports—anyone reviewing the PR sees exactly what was tested.

My QA engineer is an LLM. Claude clicks buttons, resizes viewports, toggles dark mode, and screenshots everything. When it finds a bug, it fixes the code and re-tests. Every PR now comes with proof that it works.

Newsletter SaaS: $10-30/month, features I don't need, data I don't own Claude + Cloudflare Worker: 30 minutes, 42 lines of code, subscribers sync to my GitHub repo nightly Shipped in 30 min instead of spending hours comparing SaaS options. granda.org/en/2026/01/07/…

@trq212 @bcherny 12 likes is crazy for something that I live in more than my shell

@bcherny 12 likes is crazy

Introducing Sonnet 3.7 and Claude Code, Anthropic’s new agentic coding assistant. The team and I have been hacking on Code for a while — can’t wait to hear what everyone thinks. anthropic.com/news/claude-3-…

@omarsar0 Thanks for the shout out! Happy to answer any questions

Cool setup to run Claude Code agents in parallel from your phone.