alanning

Fun project, but I also really liked the way she came up with it:

I was doing a little creative exercise the other day around the word "Overgrowth”…

Is this a common thing in the creative space? Seems like a fun activity

Is the intended use to improve automation by agents during verification? To make it easier to drive Godot apps during e2e tests, for example?

I think the most interesting part of this story is actually the Playwright-style “driver” that they built into their new apps to support faster verification by the agents.

Hopefully they will write more about that in the future.

Not sure if they edited the article after you read it but this is the 3rd paragraph now:

“Taking antiviral tablets for 8 to 12 weeks can cure more than 95% of cases.”

Off-topic but is there an effort to test AI models against code versions with major historic bugs (Heartbleed, GHOST, log4j, etc)? Seems like the kind of thing that would be relevant in security-related AI benchmarks.

For those looking for help with SOC2 compliance, I had a good experience with another YC company, Vanta. That was some years ago so not sure if anything has changed since then but I would recommend checking them out.

This is a great example for educating devs on the dangers of “set” operations vs. “pull/delete” in contexts where data can be edited concurrently.

I would say that the audit log was accurate, though, even though the bad UI design caused unintended consequences.

I appreciate the time and effort they put into writing that. Interesting to see not only their own art but also the examples from other artists.

Any recommendations for getting exposure to other on-the-way-to-being-popular artists like the X-Ray one that was highlighted?

My wife and I got a kick out of your “Games at Dave's house” example. Thanks for sharing

Thank you for sharing this.

Regarding feedback on whether sandboxing would be useful, yes, please! Including something like Docker sandboxes would make isolating the agent env’s much less of a hassle.

As an aside, I’m curious how others are handling this now… Mostly just creating dedicated user accounts?

Google’s efforts there seem laudable. They have an internal db for tracking issues that employees identify, resolve them promptly (according to the notes in the db and their response to the article authors), and generally seem to be taking the issues reported seriously.

I have more trust for google after reading that, which is not what I expected

That is incredible