Building AI that does things @openclaw 🦞 Former founding engineer @continuedev
San Francisco
Joined September 2012
- Tweets103
- Following1.1K
- Followers257
- Likes357
Dallin Romney retweeted
1/ We're reimagining your computers as shared spaces for your team and its agents.
Today we're excited to share Cua Spaces Teams and Pro, built on Cua Driver, our virtualization stack and remote desktop protocol. On macOS, Linux and Windows.
Start free: cua.ai
Dallin Romney retweeted
Today we announced the preview of Microsoft Autopilot is rolling out to our first customers - "Autopilot is a persistent, proactive and personal agent that keeps working even when you’re not"
It's been a while since I updated you all on what we are building. First Scout is now Autopilot, and my team leads building this personal agent.
We are building Autopilot on @openclaw, working with @steipete and the OpenClaw Foundation to make it a fantastic enterprise grade runtime.
blogs.microsoft.com/blog/202…
Re-introducing Sebastian, my Autopilot - and he is as excited as I am!
found it. @trycua downright impressive what it was doing, capturing and uploading screenshots to github
Dallin Romney retweeted
Let's talk Security at @openclaw. 1,788 Reports filed to us from security researchers and community, and believe it or not most were junk, and only 17 were deemed "critical". Read up on how we are tackling security openclaw.ai/security
Good things coming!
Lots of discussion with @openclaw maintainers today about improving the upgrade process. Two big things:
🧵
Dallin Romney retweeted
OpenClaw 2.0 has arrived
openclaw.ai/blog/openclaw-2-…
Think I've been seeing the word "provenance" 100x more in the age of AI. Models are changing the lexicon.
Dallin Romney retweeted
OpenClaw is maturing.
Today we’re introducing monthly extended-stable releases with backported security and reliability fixes, along with a public maturity scorecard for tracking which features are ready for critical workloads.
openclaw.ai/blog/extended-st…
If you're not able to put how you work into words, you could probably be doing it better
If you ARE able to put it into words, you can probably automate yourself away
New Blog Post: Introducing the OpenClaw Foundation
openclaw.ai/blog/introducing…
New Blog Post: Introducing the OpenClaw Foundation
openclaw.ai/blog/introducing…
Last month: "this engineer keeps complaining instead of just kicking off an agent to fix it"
This month: "my agent keeps complaining instead of just kicking off a subagent to fix it"
OpenClaw broke 100k prs this week
And also 10k merged prs
That means 90% of PRs have been closed
A lot of slop filtering happening. Could probably be more.
We've got mobile apps!
OpenClaw is now on iOS + Android 🦞
📱 Native mobile apps, finally
💬 Agents in your pocket
🔔 Channels, tasks, replies on the go
Run agents from wherever your thumbs are.
iOS: apps.apple.com/us/app/opencl…
Android: play.google.com/store/apps/d…
Dallin Romney retweeted
1/ We had early access from @GoogleDeepMind to Gemini 3.5 Flash's native Computer Use. On Cua-Bench it posted the highest mean reward of any frontier model we tested - 0.267, on KiCad tasks no model fully solves. At Flash speed and cost.