I work on that team! We're growing extremely rapidly (I joined 4 months ago from GDM and I'm at the 50th percentile of tenure), if you're interested in E2E model training reach out at https://microsoft.ai/careers/
We actually use gVisor (as stated in the article) and it has a very nifty feature called checkpoint_restore (https://gvisor.dev/docs/user_guide/checkpoint_restore/) which lets us start up sandboxes extremely efficiently. Then the filesystem is just a CoW overlay.
I submitted this HN link with a title that exactly matches the one on the article, but I didn't write the title on the article. AFAIK HN posts should match the title of the article they link to.
Canvas actually has a mix of this sandbox (with a different container) and fully client-side.
The "run" option for generated code was removed due to underutilization, but the sandbox is still used for things like the data analysis workflow and running extensions amongst other things. It's really just a general purpose sandbox for running untrusted code server-side.
That's a good question! It's not incompatible, it's just a matter of getting the flow right. I can't comment too much on that process but I'm excited for the possibilities there.
Oh hey! I ghost-wrote an earlier article that references the same idea (https://blog.google/technology/ai/bard-improved-reasoning-go...). I wonder if they came to it independently or if they read mine and it planted some seeds? Either way, super cool work.
Very cool, but some basic stuff is broken having used the app. For example, I'm unable to create a new conversation since I'm unable to click on a contact after having searched for their name in the "New Chat" flow. Looking forward to using it once this is fixed!
Edit: Seems like I have to double tap instead? Not super easy to use but it works so I'll take it!
https://microsoft.ai/wp-content/uploads/2026/06/main_2026060...