undefined | Better HN

0 pointsben_w2y ago0 comments

I said it would give you instructions, not do it for you. Do you really think that's infeasible compared with everything else they're good at?

Fraud being illegal is why I used it as an example. Fully automated fraud is to one-on-one fraud as the combined surveillance apparatus of the Stasi at their peak is to a lone private detective. Or what a computer virus is to a targeted hack of a single computer.

Sign flip: https://www.theverge.com/2022/3/17/22983197/ai-new-possible-...

Also remember that safety for AI, as AI is an active field of research, has to be forward facing to prevent what the next big thing could do wrong if the safety people don't stop it first, and not what the current big thing can do.

0 comments

peyton2y ago

Nobody’s taking those instructions and building out a lab successfully who doesn’t already know what they’re doing haha.

What have the safety people stopped so far? That’s where I’m struggling to see the point.

ben_wOP2y ago

> Nobody’s taking those instructions and building out a lab successfully who doesn’t already know what they’re doing haha.

Long may it remain so; but you can only be sure of that by having some people trying to red team the models you release before publishing the weights. If you don't, and the model can, you can't ever undo publication.

Getting the models good enough to do that seems extremely plausible to me, given what else they can do.

> What have the safety people stopped so far? That’s where I’m struggling to see the point.

Meta's in particular, or AI safety in general?

If the former: Meta's AI safety people get in the news so little I didn't know they had any until today, let alone what they have achieved.

If the latter: see the initial report on GPT-4 and all the stuff they could get it to do before public release. Some of the outputs were redacted from publication even in that report.

https://cdn.openai.com/papers/gpt-4.pdf

peyton2y ago

I just don’t see the danger. There isn’t anything you couldn’t find on 4chan in a few clicks. And the bioweapons example is a pointer to RefSeq? Come on.

These efforts just don’t stand up to scrutiny. They risk appearing unserious to people outside the responsible AI world. I think there are better places to spend time.

Edit: > If you don't, and the model can, you can't ever undo publication.

We’re talking about a model trained on published information. You already can’t undo publication.

2 more replies

j / k navigate · click thread line to collapse

0 pointsben_w2y ago0 comments

I said it would give you instructions, not do it for you. Do you really think that's infeasible compared with everything else they're good at?

Sign flip: https://www.theverge.com/2022/3/17/22983197/ai-new-possible-...

0 comments

peyton2y ago

Nobody’s taking those instructions and building out a lab successfully who doesn’t already know what they’re doing haha.

What have the safety people stopped so far? That’s where I’m struggling to see the point.

ben_wOP2y ago

> Nobody’s taking those instructions and building out a lab successfully who doesn’t already know what they’re doing haha.

Getting the models good enough to do that seems extremely plausible to me, given what else they can do.

> What have the safety people stopped so far? That’s where I’m struggling to see the point.

Meta's in particular, or AI safety in general?

If the former: Meta's AI safety people get in the news so little I didn't know they had any until today, let alone what they have achieved.

If the latter: see the initial report on GPT-4 and all the stuff they could get it to do before public release. Some of the outputs were redacted from publication even in that report.

https://cdn.openai.com/papers/gpt-4.pdf

peyton2y ago

I just don’t see the danger. There isn’t anything you couldn’t find on 4chan in a few clicks. And the bioweapons example is a pointer to RefSeq? Come on.

These efforts just don’t stand up to scrutiny. They risk appearing unserious to people outside the responsible AI world. I think there are better places to spend time.

Edit: > If you don't, and the model can, you can't ever undo publication.

We’re talking about a model trained on published information. You already can’t undo publication.

2 more replies

j / k navigate · click thread line to collapse