Building new interfaces. Prev. Meta, consumer startups.

San Francisco, CA
Joined June 2023
Hi everyone, I’ve been working on a new project called Paceman. It lets you keep an eye on your coding agents wherever you go. Key features: - Stream Codex and Claude Code status from your Mac and @omarchy desktops to your iPhone and Apple Watch - Works on top of @Tailscale so you can keep your devices connected privately, without exposing your machines to the open web - Forward agent state to Bluetooth wearables you can hack, like my modified @Pebble watch (firmware included in the repo) It’s also fully open source, so your agents can help you understand the code, get set up, troubleshoot, or customize it to your liking. Paceman started from a simple personal need to keep my ESP32 watch connected to my desktop while I’m outside. But along the way, I realized there’s a broader set of needs it can serve to make it easier to work with agents on the go. We are building the future with agents. So why shouldn’t we be able to carry great gear of our choice that helps us build more calmly and comfortably, wherever we are? Agents work in parallel and in the background, so why not have them work around what works for us, instead of being tied to our desks supervising them all day? So now, I’m building Paceman as an open personal gear system for agentic engineering. Whether you’re using devices you already love or hacking something of your own, I want Paceman to make it easier to get that gear connected and working with your agents. I’m hoping to find a few other builders who might find this useful. If you’re interested, check out paceman.ai to get started. Feel free to comment or DM, and I’ll be happy to answer any questions and help you get set up. Appreciate any feedback, thanks!
4
1
6
576
James Im retweeted
Shop your screenshots 🧢
5
4
2
98
3,806
Ahh so that’s why I was recommended this video the other day. Isn’t it funny? AI is a ship that leaks from the top.
OMG the Tesla Roadster just flew in the air!
1
85
paceman.ai website I wasn’t planning to make a marketing website for Paceman yet. I just wanted Claude to stay busy for the demo, so I asked it to put together some launch visuals and left the house. Whenever it finished, I kept sending it whatever follow-up came to mind from my phone, mostly to keep the watch showing “Working” for the video. By the time I got home, we had pretty much the website you see here. I thought it captured the feel of Paceman and communicated the concept well, so we refined the copy, polished the details, and published it. Long story short, I basically said, “I’m going for a walk. Make yourself useful while I’m out.” Which is the whole point of Paceman.
1
82
If anyone is building cool new hardware that can interact with coding agents, I’d love to try it and see if I can plug it into Paceman. I’m also open to helping build the phone and desktop companions for your device. If someone comes to mind, I’d appreciate an intro!
Hi everyone, I’ve been working on a new project called Paceman. It lets you keep an eye on your coding agents wherever you go. Key features: - Stream Codex and Claude Code status from your Mac and @omarchy desktops to your iPhone and Apple Watch - Works on top of @Tailscale so you can keep your devices connected privately, without exposing your machines to the open web - Forward agent state to Bluetooth wearables you can hack, like my modified @Pebble watch (firmware included in the repo) It’s also fully open source, so your agents can help you understand the code, get set up, troubleshoot, or customize it to your liking. Paceman started from a simple personal need to keep my ESP32 watch connected to my desktop while I’m outside. But along the way, I realized there’s a broader set of needs it can serve to make it easier to work with agents on the go. We are building the future with agents. So why shouldn’t we be able to carry great gear of our choice that helps us build more calmly and comfortably, wherever we are? Agents work in parallel and in the background, so why not have them work around what works for us, instead of being tied to our desks supervising them all day? So now, I’m building Paceman as an open personal gear system for agentic engineering. Whether you’re using devices you already love or hacking something of your own, I want Paceman to make it easier to get that gear connected and working with your agents. I’m hoping to find a few other builders who might find this useful. If you’re interested, check out paceman.ai to get started. Feel free to comment or DM, and I’ll be happy to answer any questions and help you get set up. Appreciate any feedback, thanks!
1
5
247
Addressing some early feedback: Q: Can I approve requests and take actions directly on the watch? A: Not yet, but I’m looking into it. Lightweight interactions are definitely on the roadmap. Q: Why @Tailscale? A: It lets your phone get agent status directly from your computers over a private connection. Much simpler than building and running a centralized Paceman service.
1
21
James Im retweeted
Walter Ballmer’s designs for Italian company Olivetti from the ‘60-70s are such a good color study
9
99
699
16,421
James Im retweeted
I'm back, from my 4-week phishing trip away from X. apologies to anyone who got DM'd an invite from me to the same phishing trip that I fell for 🥲
2
1
7
1,951
If you want to work with me at @triggerdotdev, we're hiring backend engineers, a dev marketer, a devrel (SF) and a design engineer 😃
45
15
173
11,979
I don’t care anymore I just rip it on astra fast
1
3
267
Not to be dramatic, but I've experienced a huge downgrade in quality of life over the last 24 hours. I'm testing the fresh install experience, so I keep losing Codex status on my watch. Can't live without it now!
This week I started routing Codex agent status and usage left to my Apple Watch. It’s been super useful for keeping an eye on my agents at a glance whenever I step away from my desk to make a coffee or go on a walk. Even when I’m at my computer, the work is so async and chaotic at this point, it’s been nice to keep track of who’s still working, who’s done, and who needs help, all in one place on my menu bar. This started with wanting to connect custom hardware to my phone so it can talk to agents on my computers wherever I go. But once I had the status syncing, I thought, why not just show it on the Lock Screen and Apple Watch too? Honestly, it’s been a game changer. Still want to explore other quiet, ambient ways to interact with agents though. For example, a custom Pebble watch face + Live Activities on the phone could be a great combo.
1
145
James Im retweeted
I’m looking for an extremely high-agency engineer to join us at Adam. Bonus points if you’ve been a founder or know your way around CAD. We’re growing an average of 50% MoM and have a real shot at defining this category. If you want to build the future where we vibe-CAD hardware, DM me.
We are now entering into an era where any product can be created exactly to a consumer's preferences & needs. I vibe-fabricated a dog door with a wifi-controlled lock, perfectly to the specifications & design of my house. I know nothing about metal fabrication or electrical engineering. It's now getting manufactured and delivered in 2 weeks -- for almost the same cost if I bought a mass-produced item off-the-shelf.
13
10
1
178
20,631
This week I started routing Codex agent status and usage left to my Apple Watch. It’s been super useful for keeping an eye on my agents at a glance whenever I step away from my desk to make a coffee or go on a walk. Even when I’m at my computer, the work is so async and chaotic at this point, it’s been nice to keep track of who’s still working, who’s done, and who needs help, all in one place on my menu bar. This started with wanting to connect custom hardware to my phone so it can talk to agents on my computers wherever I go. But once I had the status syncing, I thought, why not just show it on the Lock Screen and Apple Watch too? Honestly, it’s been a game changer. Still want to explore other quiet, ambient ways to interact with agents though. For example, a custom Pebble watch face + Live Activities on the phone could be a great combo.
1
1
1
13
914
Perfect timing
Global reset landing tomorrow 10am PST for all paid ChatGPT accounts. Apologies for the slow start with GPT-6.1 Sol, it's now back to running at expected speeds after the massive load spike in the first two days.
1
209
I'm holding 10,000 synthetic neurons in my hand. In the podcast below, more of the story of how we got here, and the foundations behind what we built (thanks @fdotinc). 🔽 Prima-Lux: our first artificial brain in silicon. We can't wait for people to try it!
We brought in a founder building synthetic neurons. His goal is to sell the first artificial brain, to a robot. He gave a brief tutorial on how to make one: 22:47 Building a synthetic neuron from scratch 24:15 Making a robot move using only synthetic neurons 28:33 Dendrites, cell bodies + axons with hardware 32:42 Turning sensor data → spikes → movement 34:11 The roadmap to a full synthetic brain 38:00 A breakthrough in synthetic memory By the end, we weren’t really talking about robots anymore...
10
6
1
63
4,017
James Im retweeted
I have a G4 iMac with a Mac Mini inside that I use as a server. I asked Claude Opus to recreate an almost pixel-perfect MacOS X 10.2 desktop with a Finder face and some widgets to monitor how everything is running. It gave it expressions based on CPU state, a pretty close genie effect, a PiP view of the real desktop and a sleep mode that turns on at night.
37
87
7
1,098
64,217
we're about to get so many cool new AI wearables
Apple has also been working on an AI pendant with a camera, though that project has been postponed. The device was conceived as something users could wear as a necklace, attach to clothing or place elsewhere on the body, gathering visual data for processing by the new Siri AI.
1
321
things like this didn't happen when we typed SwiftUI by hand: `models.filter { $0.isSupportedWhenUsingCodexWithAChatGPTAccount }`
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
1
225
never mind it's working now
39