I do basically the same. Have multiple Docker sandboxes where I let agents yolo.

Must say I don't really love the setup. The workflow is not as frictionless as just opening Claude Code used to be.

American Ocean incoming?

I'm waiting for west america (asia and oceania) and east america (europe and africa). And maybe "very south america" for antarctica

I think you might have missed the latest onion: https://www.theguardian.com/us-news/2026/oct/22/trump-atlant...

Canada > America North

He's literally "joked" about it

Homework assignments ungraded but mandatory.

Then an in-class oral exam on a random subject drawn at exam entry.

Works great in my country.

At the end of the day, the responsibility is on the student to study.

How does it compare to docker sandbox? (That relies on microVMs)

xD

How does it compare to ElevenLabs?

It's a plug-and-play framework for recursive agent harnessing. In an open world, agents encounter tasks unseen during the harness design. Harness² is designed for this exact scenario.

From the look of the website, I’ve come to understand that SI is short for slop intelligence.

That's not how I'm reading it. More like, given the past 3 years development, why wouldn't AI be able to do that in the not-so-distant future?

Using AI for design will always be derivative. For many cases that is good enough but for good product design, a human element will most likely always be necessary. Until the machine gains the ability to do just that