[giancarlostoro]

I usually have Claude confirm with me but I've seen it close it if its a unit test that passed for example.

[maleldil]

You can't trust it 100%. Sometimes it will just refuse to fix a compiler or lint warning (often saying "This was a pre-existing issue...") or write a trivial test that does nothing and always passes.

[0x457]

> writes code with a lot of warnings > compacts > "This was a pre-existing issue..."

I still take this over writing code myself though.

[maleldil]

I'm not saying you shouldn't. I'd say 70% of my work code is written by Claude Code or Codex. But this is something you should be aware of when interacting with agents.

[giancarlostoro]

Point being that there are multiple gates to one story, including human testing as one of them.