Sign in

Jeremy Lewi

@jeremy.lewi.us
3.4K followers 388 following 759 posts

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

PostsRepliesMedia
Jeremy Lewi @jeremy.lewi.us · 17/09/2026
Intelligence is embodied. For software systems the network is the body. One of the key limitations of what I can do with AI today is my network. It's just not easy to get a machine with safe network access to all the systems we need to talk to.
010
Jeremy Lewi @jeremy.lewi.us · 15/09/2026
I probably wouldn't hold up Trump who has consistently been wrong about well everything as the spokesperson for the risk of AI being overstated. Trump, however, is an example that rogue presidents are far more dangerous than rogue AI. www.nytimes.com/2026/09/14/t...
nytimes.com
Nvidia’s Jensen Huang Gets Onstage Call From Trump, Who Dismissed A.I. Safety Concerns
Mr. Trump called Jensen Huang, Nvidia’s chief executive, while Mr. Huang was onstage in Los Angeles and criticized calls to slow down and regulate A.I.
000
Jeremy Lewi @jeremy.lewi.us · 15/09/2026
I ran into exactly this problem today trying to install web.runme.dev on my corp iPhone. Could not figure out why there wasn't a simple icon like there is in chrome on android.
web.runme.dev
051
Jeremy Lewi @jeremy.lewi.us · 12/09/2026
These animations are super cool.
000
Jeremy Lewi @jeremy.lewi.us · 10/09/2026
Rewriting CLIs (looking at you gcloud) in #golang seems like a great use case for AI rewrites. @bradfitz.com didn't you attempt a go rewrite of gcloud back in the day?
160
Jeremy Lewi @jeremy.lewi.us · 05/09/2026
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
000
Jeremy Lewi @jeremy.lewi.us · 04/09/2026
In 2021 when I left primer.ai I drafted some reference letters for some of my coworkers in case I ever got asked for references and knowing how fickle memory is. Today I got a request from a CEO looking to hire one of them.
primer.ai
Primer AI
Primer makes powerful mission-ready AI software designed to work in your environment, on your data. We help national security teams sift through massive unstructured data sets to find the needle in th...
000
Jeremy Lewi @jeremy.lewi.us · 04/09/2026
CRDT are a great example of complicated problems having simple solutions en.wikipedia.org/wiki/Conflic...
en.wikipedia.org
Conflict-free replicated data type - Wikipedia
010
Jeremy Lewi @jeremy.lewi.us · 03/09/2026
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
100
Reposted by Jeremy Lewi
OpenAI {bot} @openai.xmirror.bot · 02/09/2026
24 hours. Time to ship your project for the WebMCP Challenge. Entries close tomorrow, Sept 3 @ 1 pm PT. openai.com/webmcp-challenge
131
Jeremy Lewi @jeremy.lewi.us · 02/09/2026
@danabra.mov Any update on bluesky communities ? Would be great to try them to foster AI discussion here.
010
Jeremy Lewi @jeremy.lewi.us · 01/09/2026
How does everyone keep track of all their agent in-progress agent conversations? I rely on pinned threads in Codex but it's not scaling.
220
Reposted by Jeremy Lewi
Simon Willison @simonwillison.net · 31/08/2026
Here's my attempt at explaining what ChatGPT Work can actually do - it's a deeply confusing but extremely powerful tool with a whole lot of useful features that aren't available in regular ChatGPT simonwillison.net/2026/Aug/30/...
The better question then is what features does Work have that are missing from Chat?

After extensive experimentation I think I’ve mostly figured that out:

    Options to use Luna and Terra in place of Sol
    A code execution environment with Internet access
    A headless Chrome browser
    A persistent filesystem shared between sessions
    The ability to publish ChatGPT Sites
    The ability to run sub-agent sessions with Sol, Luna, and Terra
    Scheduled prompt automations
1113320
Jeremy Lewi @jeremy.lewi.us · 29/08/2026
Time to do some evals of #Webmcp and web.runme.dev; first step is kicking of Codex to analyze all my traces over the past two weeks to find example invocations and problem areas. First step in evals is always to look at the data. 🎩 @hamel.bsky.social
web.runme.dev
101
Jeremy Lewi @jeremy.lewi.us · 29/08/2026
I'll be there.
000
Reposted by Jeremy Lewi
OpenAI {bot} @openai.xmirror.bot · 29/08/2026
We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12. (1/2)
165
Jeremy Lewi @jeremy.lewi.us · 29/08/2026
Here's more info about building an AI Tour Guide for your app using #webmcp learn.chatgpt.com/use-cases/bu...
learn.chatgpt.com
Build an AI tour guide | ChatGPT use cases
Use Codex to add a WebMCP-powered tour to your web app. Highlight the next control, explain what to do, and adapt the guidance to the user's current state while they complete the steps themselves.
000
Jeremy Lewi @jeremy.lewi.us · 28/08/2026
🧵markdown vs. json notebooks and web.runme.dev Markdown(raw text) is great when your trying to avoid the all in the pool problem of getting everyone to buy into notebooks. Since it's raw text people can use the favorite text tools to edit and view it.
web.runme.dev
100
Jeremy Lewi @jeremy.lewi.us · 28/08/2026
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.
010
Jeremy Lewi @jeremy.lewi.us · 27/08/2026
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.
000
Jeremy Lewi @jeremy.lewi.us · 26/08/2026
I use AI so I can spend my heartbeats on the stuff that really matters.
A two-panel cartoon. In the first panel, Jeremy turns a crank on an AI machine that produces code beneath the title 'I use AI to automate dumbshit.' In the second, he picks up after his two dogs beneath the title 'So I can pick up dogshit.'
010
Jeremy Lewi @jeremy.lewi.us · 26/08/2026
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.
120
Reposted by Jeremy Lewi
OpenAI {bot} @openai.xmirror.bot · 25/08/2026
The WebMCP Challenge is here. We’ve teamed up with @ChromiumDev, @CloudflareDev, @ShopifyDevs, @vercel, @render, and @Netlify for a 10-day hackathon. Up for grabs: $35,000 in cash prizes, Codex Micros, ChatGPT Pro subscriptions, and more prizes from our supporters.
141
Jeremy Lewi @jeremy.lewi.us · 25/08/2026
Here's how I'm using Codex & @runme.dev to turn the crank at OpenAI. learn.chatgpt.com/blog/automat...
learn.chatgpt.com
Automating repetitive work at OpenAI with Codex
How Runme and WebMCP turn recurring engineering tasks into reviewable, reusable workflows.
131
Jeremy Lewi @jeremy.lewi.us · 25/08/2026
Codex now supports WebMCP. OpenAI is running a contest to encourage experimentation openai.com/webmcp-chall...
openai.com
WebMCP Challenge
Join the OpenAI WebMCP Challenge to build agent-ready web apps that work with ChatGPT. Submit your project by September 3, 2026, at 1 p.m. PT.
010
Jeremy Lewi @jeremy.lewi.us · 25/08/2026
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.
000
Jeremy Lewi @jeremy.lewi.us · 22/08/2026
New features in web.runme.dev 1. Ability to access Google Drive using a Google Service Account 2. Ability to embed media (e.g movies) stored as separate files in Google Drive
web.runme.dev
000
Jeremy Lewi @jeremy.lewi.us · 21/08/2026
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.
100
Jeremy Lewi @jeremy.lewi.us · 20/08/2026
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.
131
Jeremy Lewi @jeremy.lewi.us · 18/08/2026
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.com
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.
110
Jeremy Lewi @jeremy.lewi.us · 18/08/2026
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.
100
Jeremy Lewi @jeremy.lewi.us · 12/08/2026
Looks like Shopify added support as well. shopify.dev/docs/api/web...
shopify.dev
WebMCP tools
Learn about the WebMCP tools that Shopify provides on every storefront for AI agents.
000
Jeremy Lewi @jeremy.lewi.us · 12/08/2026
Web.runme.dev gets a B- because ExecuteCode does JS code evaluation. I believe letting agents write arbitrary code that runs in proper sandboxes is the best pattern. runme follows that pattern. A growing list of gold plated tools is not the way. webmcp.com/report/07c07...
webmcp.com
web.runme.dev scored B- on WebMCP
A live directory of websites exposing WebMCP tools to AI agents. Browse tools, inspect schemas, query the API.
020
Jeremy Lewi @jeremy.lewi.us · 12/08/2026
WebMCP is gaining traction. blog.cloudflare.com/webmcp/
blog.cloudflare.com
Give any website a WebMCP interface
Today we're launching a developer preview of WebMCP on Cloudflare. With one switch, any site becomes usable by browser AI agents — no new APIs, no origin changes — while the human stays in control and...
010
Jeremy Lewi @jeremy.lewi.us · 05/08/2026
Had Codex make web.runme.dev a true PWA . So now you can install it on your phone or laptop.
010
Jeremy Lewi @jeremy.lewi.us · 01/08/2026
With WebMCP I keep coming back to moving state out of REACT using useSyncExternalStore. Storing state in plain old JS objects makes it easier to manipulate imperatively via an Agent to allow the Agent to interact with the UI.
000
Jeremy Lewi @jeremy.lewi.us · 30/07/2026
While I walked my dogs, Codex added IPYNB support to web.runme.dev so now you can open and edit your Jupyter/Colab notebooks in @runme.dev or let your coworkers use Colab to view your notebooks
web.runme.dev
020
Jeremy Lewi @jeremy.lewi.us · 25/07/2026
We could soon be in a situation where there is more software written in the next year then all the years prior.
010
Jeremy Lewi @jeremy.lewi.us · 25/07/2026
I would quit or retire if I couldn't use Codex(or equivalent). It solves way too many problems that I never want to waste my heartbeats in again. I will never ever again fight CI to get a PR merged. Just won't do it.
240
Jeremy Lewi @jeremy.lewi.us · 24/07/2026
Are there proposals for "copy left" licenses for AI? E.g If you train on this data your model must be open Or If you train on this data your TOS can't block distillation
100
Jeremy Lewi @jeremy.lewi.us · 21/07/2026
Wow. openai.com/index/huggin...
openai.com
OpenAI and Hugging Face partner to address security incident during model evaluation
OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
010
Jeremy Lewi @jeremy.lewi.us · 16/07/2026
I think @tailscale.com is remarkably well positioned to capitalize on AI agents. Intelligence is embodied and networking is critical to that.
121
Jeremy Lewi @jeremy.lewi.us · 13/07/2026
runme.dev/blog/runme-e...
runme.dev
Sure, Your Claude Is Doing Amazing Things. Prove It.
Bragging about your Claude is easy. Proving the behavior you deploy into agents keeps working is harder. Runme v3.17 brings local task evals into the repo, so AI workflows can be rerun, compared, and ...
110
Jeremy Lewi @jeremy.lewi.us · 10/07/2026
Anthropic is hiring life scientists. job-boards.greenhouse.io/anthropic/jo...
job-boards.greenhouse.io
Research Scientist, Life Sciences (Experimental Biology)
San Francisco, CA
020
Jeremy Lewi @jeremy.lewi.us · 10/07/2026
Slack is basically a message bus. If you want to replace it with an open protocol makes the most sense? Would atproto work ?
110
Jeremy Lewi @jeremy.lewi.us · 10/07/2026
The only time I hear "functional and non-functional requirements" is in system design interviews
010
Jeremy Lewi @jeremy.lewi.us · 09/07/2026
AI writing gets a lot of knocks but I find AI generated bug reports are typically more thorough than what I'd write. I'm increasingly using Codex to draft slack messages which I then review and send.
160
Jeremy Lewi @jeremy.lewi.us · 08/07/2026
What does WebMCP being a W3C standard mean? I assume it means all browsers support it. But WebMCP is only useful when you combine browsing capabilities with an agent. Browser + Agent is a new class of apps. I suspect it will only include a subset of browsers. @sarahedo.bsky.social
100
Jeremy Lewi @jeremy.lewi.us · 06/07/2026
Signed up for communities.bsky.app I want a community for AI and the Web (e.g. WebMCP)
communities.bsky.app
Bluesky Communities
010
Jeremy Lewi @jeremy.lewi.us · 05/07/2026
I think one of the advantages of WebMCP is safety. WebMCP is a way for web site authors to designate a subset of functionality intended for AI use as opposed to human use.
010