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
And hope that others do as well.
Then we we go through a bunch of other stuff in the less wrong post, but I guess how how do we evaluate it is based on years of doing various different projects and thinking about what's likely to work w which does include things that seem unlikely to work but very high impact if they do and how likely they are to work, which a lot has to do with whether the person has a strong hunch that the world generally doesn't accept or they
They've developed complex stuff and people object to it for silly reasons, like Graziano, for instance.
I I I think it's interesting to consider that the things we set out to do we assume are individually unlikely to work but very high impact if they do.
However, you asked what things haven't succeeded, and actually we have succeeded with the things we've set out to do so far.
And I I am uh somewhat surprised by that, but also I think we're s good at picking the things which we will say at the beginning are very unlikely to work and people would assume
are unlikely to work, but then wind up being pretty high impact.
Although with the Graziano work, we tried a lot of different things that didn't work an until we hit upon this.
I think sticking with a thing when people are inclined to give up like something that's very R and D heavy to if a strong hunch for it is quite valuable to keep going even if after you have failed in various different ways to start with.
is interesting to consider is just as you can take a neglected approach to doing what is the highest impact stuff in alignment technically, you can also do that in terms of policy and other things too.
That meta approach led us to conclude it would be worthwhile to encourage the creation of for profit consulting businesses, of like more non profits doing neglected approaches, of individuals setting out to do neglected approaches, of
field building to get brilliant people into different fields like this in particular, but also many other fields to to get nerd sniped into caring about and doing something to do with alignment.
We think there's a lot of loading in freak there.
And also it also incidentally neglected approaches to AI policy specifically can be things like getting government to increase funding to alignment research actually moves forward alignment, not just capabilities.
doing things like uh increasing whistleblower protections, for instance, very high impact, quite quite neglected today, getting Republicans to care more about AI safety and trying to prevent it from becoming a partisan issue.
Like the more f far left is like tied up AI safety unfortunately, too much in things that are on the surface to people on the right, like woke D EI associated.
Uh
But that actually has nothing to do with AI alignment.
Like making the founding fathers black is a failure of AI alignment.
The system is not aligned, it's not demanding what you told it to do.
Showing 561–580 of 589 · page 29 of 30
← Previous
Next →