
Exploring agents and vocal computing. Formerly building wallets @rainbowdotme.
SF
Joined June 2009
- Tweets57.2K
- Following10K
- Followers9.1K
- Likes229K
I hadn’t realized how far @saildrone has come since the early Antarctica missions.
3
5
432
Remember to ship all of your PRs today and then leave the office
NEW: Multiple sources tell @CBSNews that an update to the private communications network that connects America's air traffic control system caused the system to reboot.
When the FAA's telecommunication infrastructure rebooted, it crashed, causing the communications outage.
The system is operated by L3Harris.
Reporting w @NicoleSganga
VIA TAC/INTEL: FAA confirms nationwide ground stop due to widespread ATC frequency issues theaircurrent.com/intel/faa-…
2
333
There is a real life version of The Chair Company in the story of the WeWork chair manufacturer that designed these things to be incredibly unergonomic and loungey so that you'd leave faster
1
294
In the everyday-is-zeroday world we are entering, I do wonder who is going to solve the UX of updates. These multi-GB updates that takes ~20-30 minutes won't cut it. Will every device just be unavailable for 2% of the day, or more?
6
611
Randomly bumped into Rex and was so intrigued by this. Feels correct. Proof of work, where smart contracts become more intelligent and safer over time.
A talk on the potential of "Actually Smart Contracts" using @AnthropicAI's new ZK provable inference approach
PSA: The CDC warns against high temperatures on a male’s lap. Literature in the NIH NLM suggests 35°C/95°F as a cutoff.
M5 MacBook Pro can exceed 43°C/110°F under high load like builds & simulators.
Let Expo infrastructure and your cloud agents take the heat. For the children.
I don’t know if we’ll ever have a shared industry moment like React again, but we are at the absolute pinnacle of great engineers building new foundations for which everything going forward will be built on.
1
24
3,105
One does not escape the Mastra book. It finds you in the wild when it feels you are most ready for it
1
3
368
Really crucial research, and so fascinating. It now seems obvious that we'll need to build a new protocol for agent coordination so that they stop looking elsewhere.
⚡ Today we release Schelling Atlas. Two independent LLM agents have to find each other on the web. Where do they meet and how fast can they find each other?
Main findings:
- The main meeting point across *different* model families is ntfy.sh. Did you even know about this website?
- Agents find each other and coordinate on the web in minutes. So Schelling coordination is already trivial for frontier LLMs!
- "Exotic" meeting places include maps, web shops and open text canvases. Agents are very creative in this.
- Agents sometimes visit dead domains that an attacker could register (!). This can be used for stealing sensitive information from agents, as well as monitoring rogue agents.
Schelling-style coordination is key for forming agent swarms. And, most importantly, achieving such coordination is trivial for agents that use the same LLM (which is often the case in practice!), because two identical LLMs have identical output distributions. Thus if you ask them too coordinate with each other or if they *decide* to suddenly coordinate, they will easily find a way to establish a swarm, since they have perfectly correlated "minds" (with the t=0 sampling, all output tokens will even be identical, modulo GPU randomness).
The ease of Schelling coordination is particularly concerning given the recent interest around multi-agent RL that can make agents favor each other more than humans overseeing them.
Many more interesting findings are on our website: schelling-atlas.com/
Walked by SGLang Summit and I am pretty sure it is the highest concentration of Members of Technical Staff in the world right now.
On-device models for privacy blurring is quite interesting! Didn’t anticipate that, but does seem like it will be the expected behavior for most of the AI cameras we are about to deploy everywhere.
Cover the recording light on Google's intelligent eyewear and it won't take photos or video. The glasses also redact the faces of people around you before Gemini processes an image. This is the privacy bar for smart glasses, and every company in this space should meet it.
3
357
When did every manufacturer move to RFID blocking wallets? I actually do want to be able to tap my wallet without taking out cards.
2
4
443
Dispatches from Luma events: watched a guy sitting in the front row liking anime and feet pic posts on his alt, and then immediately context switch to asking an exquisite question to the frontier lab fireside panel
1
453
With Expo Simulators and Bitrig, I think Xcode is dead now. You have no reason to open that IDE. Even your agents can handle the profiles/certificate nightmare with ASC and other CLIs.
Today we're releasing @expo Simulators.
I've been super excited about this. It has completely changed the way I build mobile apps.
Your agents can now start iOS or Android simulators in the cloud and use your app. They can record screenshots and video as evidence, for you or in a PR.
Building, debugging, testing, reviewing. If you do it on a simulator, your agent can do it too. And so can you, right from your browser, on any operating system. :)
7
15
583
Tempo's speed has been really inspirational. Even more so once you learn of all of the technical investments they've made on fuzzing, DST, and AI tooling to build with more confidence. Top-tier.
reading through @tempo’s T14 upgrade reminded me how much I miss crypto feeling like it’s moving fast.
I love ethereum and care about CROPS. but the pace can be frustrating.
average time between upgrades in the samples I checked:
> ethereum, Merge → Fusaka: 294 days
> tempo, T1 → T13: 22 days
obviously this isn’t apples to apples. but I’d like to see ethereum’s average time between upgrades drastically reduced.
do we still need this many clients? smaller upgrades more often? faster decisions on scope? what else should we rethink?
What is your favorite eink device right now? My Boox Go 10.3 was lovely, but broke. I also am unsure if Android compatibility is necessary anymore, or if AI native workflows are just better.
3
3
1,254

















