Hacker News new | ask | show | jobs
by saintfire 53 days ago
Well, they're presumably dead mains.

I really don't think it'd struggle with the correct procedure, either. It's very well documented how to test (and lock out) electrical circuits.

Whether or not they follow it correctly is another thing but it's not like you couldn't search it up and have false confidence before AI. This isn't manufacturing bombs or heart surgery in 10 easy steps.

1 comments

I agree on both counts but don’t think it’s unreasonable to have safeguards around this kind of ask. With no additional information, this flag seems overly sensitive but we don’t have the full context. I’d expect the occasional superfluous flag when you’re in this neighborhood of conversation and that that’ll happen less as models improve

My main point is _flagging_ is very different from banning.

Flagging is a minor inconvenience just start a new chat or look it up the old fashion way. Not every use case will be as serviceable by every model today.

For what it’s worth, I asked Claude with opus 4.7/4.6 it gave me an answer straight away