Matthew

@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.

Poke should be able to help with tasks behind auth walls. I gave Claude Code access to 1Password (w/ API key to isolated vault) through some Python scripts and an Agent Skill. It was a little wonky to do from Termuis, but I followed along as Playwright MCP managed a headless Chrome instance to delete some old accounts for services I haven't logged into in 10+ years. Later on I added the ability to follow along in GitHub Issues, where Claude is posting screenshots of the journey. :)

@mtt love it! is there anything we should add to Poke to make this even better?

Running 6 Claude Code agents in parallel from my phone. Here's my mobile dev setup: My Claude Code mobile setup: • Vultr VM ($0.29/hr, pay-per-use) • Tailscale for secure access • Termius + mosh (survives network switches) • Poke webhook for push notifications • tmux for session persistenceKick off a task, pocket the phone, get notified when Claude needs input.

@simonw @utotranslucence @simonw you have a hook in place or any scripting to pull your agent transcripts and ease the pain of storing them with the code commit?

@utotranslucence I've published hundreds - anything in my commit history on GitHub with the string "gistpreview" or more recently "gisthost" is a link to a coding agent transcript github.com/search?q=autho…

have any highly experienced engineers published logs or chat history from their coding work with agents for others to learn from? Where might you find them?

@stetsblake @interaction Same, the doc link is hidden a bit deep in the “create an api key” page: interaction.co/mcp

@mtt @interaction Thx! I saw something similar with pushover. I didn’t know poke had webhooks

My Claude Code on-the-go setup: - Vultr VM with 24GB running Ubuntu - Termius for mobile terminal usage (it works quite well) - Claude Code in yolo mode - Poke for push notifications when Claude needs my attention (@interaction ❤️) - tmux for session persistence (been running 6 Claude Code agents in parallel, tabbing pretty easily) - Tailscale: SSH & Mosh only reachable from the subnet All created from a single Claude Code session where I gave it my Vultr API key (through env var) and access to `gh`

@stetsblake @interaction x.com/mtt/status/200…

@mtt @interaction Wait how did you link up Poke to Claude notifications? That's sick

Wrote up my Claude Code mobile setup. Cloud VM + push notifications = async development from your phone: granda.org/en/2026/01/02/…

The key to mobile Claude Code: tmux session persistence and a webhook that sends push notifications when Claude asks a question. Walk away, get notified, respond from your phone. Async development from anywhere.

I code from my phone now. Claude Code on a cloud VM + push notifications when it needs my input. Start a refactor on the grocery store, fix a bug from the couch. Development fits in to the gaps of the day.