Comment by smashed
10 hours ago
Opus 5.5 in Claude code added a unit test checking DNS and internet access using example.com as the target on a project I'm building yesterday. It's an agent sandbox (I know, yet another), so the call was expected to fail, but still... It should have at least targeted a captive portal endpoint or a project owned domain.
I caught it in review but thousands of others won't.
That ship has sailed I would say.
If it breaks in those thousands of projects, that will be an important lesson to review your agents more carefully. So a net win?
More likely the agents will fix it as fast as they made it and people will continue not caring so much about reviewing what agents are doing for cases where they don't care so much (which is a lot of cases)