News for hackers. Stuff that matters.

A comment on Sam and Greg's response to OpenAI Safety researcher claims. Parent comment

Re:Sam and Greg's response to OpenAI Safety researcher claims by nl on Sunday May 19, 2024 @04:41AM (#40405358)
> map tool lets users “nominate targets of interest” for “the target nomination process”. She meant it helps people choose which places get bombed.

So... people are choosing who to kill?

I'm reasonably sure there are historical precedents for this.

[ Parent | on HN ]
Re:Sam and Greg's response to OpenAI Safety researcher claims by int_19h on Tuesday May 21, 2024 @04:07AM (#40425408)
The danger here is that the model hallucinates while "simplifying" and omits important information that would prevent a strike.

Or, if you're more conspiracy-minded (which is not necessarily unwarranted with the likes of Palantir), the model can be deliberately induced into "simplifying" away collateral damage through careful prompting, providing a veneer of plausible deniability.

[ Parent | on HN ]