Jeremy Lewi

@jeremy.lewi.us

Building web.runme.dev. Trying to get my hearbeats back by automating my job with AI.

I think tailcat means wireguard tunnels could be used in places where ssh tunnels currently are. Such as launching an agent on a devbox. Any guidance on when to use wireguard tunnels vs ssh? @bradfitz.com @crawshaw.io

Brad Fitzpatrick@bradfitz.com · 3w ago

I can finally talk about this, 3 years later... github.com/tailscale/ta... It's a library + CLI tool that's like netcat, but over Tailscale's data plane without any control plane (no accounts, no dependence on Tailscale the company, all open source) WireGuard + NAT traversal without IP addresses.

Finally figured out why and how to start adopting CRDTS in web.runme.dev. The goal is to create a UX that lets us continually use AI to improve our runbooks. I think we want to train a reward model that can predict whether a human would accept/reject a runbook edit.

web.runme.dev

Google figured out monorepos and CITC in the early aughts. A decade later my disk is filling up and I need to do cleanup because every worktree is taking up a mountain of space.

Could someone share this with Google Analytics? I have no idea what any of it means or how to make basic plots like breakdowns by referrer.

Chrome for Developers@developer.chrome.com · 3w ago

Create agent-ready web apps for the WebMCP Challenge → goo.gle/4qpDQYV We're excited to see ChatGPT supporting WebMCP, the experimental standard that lets users and AI agents navigate websites together. In the @openaibot.bsky.social WebMCP Challenge you can experiment with it and win prizes.

An AI tour guide for your webapp is one of the WebMCP use cases I'm most excited. Here's a demo of using Codex to walk you through the runme UI and explain how to use it. There will always be flows best accomplished through clickops. However we still need to teach users how to use the app.

One of the reasons people are rightfully against data-centers is they will likely drive up energy costs. This seems like an example of the abundance hypothesis where the answer is to speed up and build more energy not slow down.

A waymo blocks an emergency vehicle and a bunch of politicians get riled up about the dangers of AI. Meanwhile the President pardons the January 6 rioters who assaulted office rioters and vandalized the Capitol.

With Codex/Claude the bottleneck in software development is now expressing your intent. Writing the code is no longer the rate limiting step. This completely upends software development. Take issue trackers. The key problem they were solving was allocation of scarce coding resources to features.

I'm redoing ipykernel support in @runme.dev to get rid of the dependency/extra hop through Jupyter Server. That is very janky and a terrible UX. I reused Jupyter Server because the only pure go implementation of ZeroMQ github.com/go-zeromq/zmq4 is a bit dated and starved for develope cycles.

GitHub - go-zeromq/zmq4: [WIP] Pure-Go implementation of ZeroMQ-4

[WIP] Pure-Go implementation of ZeroMQ-4. Contribute to go-zeromq/zmq4 development by creating an account on GitHub.

github.com

I'm exploring document comments as a collaboration modality with Codex. As Codex handles increasingly complicated tasks for me, I rely on Codex producing documents summarizing what it did. So comments are obvious for reviewing and directing Codex.