Judd Rosenblatt
speaker
589 appearances
1 recordings
1 series
first heard Oct 2024
last heard Oct 2024
Judd Rosenblatt’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
But we don't the full economic
forces of the entire world are behind advancing AI capabilities right now as as fast as they can.
and I I think like we have to recognize that that's happening, therefore we should try to solve the alignment problem.
Ideally they don't do it too much, but there's also interesting work out out there a around doing things which are sort of like a negative
alignment tax.
I think that's a pretty exciting thing too, like doing things that increase the probability of actually solving alignment while also potentially like you advance capabilities a little bit.
The assumption though is that anything you do that makes uh AI more aligned is going to wind up uh reducing its capabilities.
But we haven't necessarily seen that historically.
What if we live in a world where it turns out that you sometimes advance where it's possible to advance alignment and then be more capable by virtue of your alignment?
Uh that that would be preferable if if that is the case.
Maybe it's not the case, maybe it is.
Uh we shouldn't overindex on that being the case.
But but if it is, that would be great.
And it would be great to find and do more neglected approaches that support and explore that possibility.
Regardless of the the the fact that AI capability
Are off to the raises like the marginal impact of some people working on AI safety doing a little bit to advance uh capabilities is orders of magnitude less than would otherwise be done.
You might as well do stuff that that winds up advancing alignment if you can, while still being responsible and having good safety plans and things like that.
I I I guess other things that are interesting from the survey are that uh both the effective altruism community and alignment community.
Communities overestimate the perceived value of intelligence in the community and underestimate the value of softer skills like collaboration and work ethic.
As soon as anyone hears, they're like, Oh yeah, of course that's the case.
Showing 341–360 of 589 · page 18 of 30
← Previous
Next →