41–50 of 70 posts
[flagged]
[flagged]
BWHAHAHAHAHA. your bot tried, but failed at the same time. (also interesting that this user's other comments seem ok-ish. The prompts are evolving, we get a sneak peek here on what they prompted for, and the delivery seems more human as well)
[flagged]
I'm willing to wager that your comment was generated from the body of the article plus a prompt to work in an advertisement for your product, which gets a mention in nearly every comment you make (and every submission you make, sometimes on a daily basis).
The problem is, 99% secure is a failing grade.
> pointing it at a few days of real traffic produced policies that matched human judgment on the vast majority of held-out requests. The problem is, 99% secure is a failing grade.
I have an issue with security layers that are inherently nondeterministic. You can't really reason strongly about what this tool provides as part of a security model.
But also, it's in an area where real security seems extremely hard. I think at some point everyone will have a situation where they wanna give an agent some private information and access to the web. You just can't do that in a way that's deterministically safe. But if there are usecase where making it probabilistically safer is enough to tip the balance, well, fine.