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
The unfortunate thing
About approaches over longer timelines is that people are more likely to abandon them as because they start to think about shorter timelines.
So I do think it is important that people with longer timelines or
good ideas for things that require longer timelines, continue to work on those neglected approaches and that funding is allocated to those like people think about the most impactful work that would take decades and then actually go set out and do that and think about the multiple big ambitious steps that need to be taken and then execute them one by one.
And also focus on the biggest unknowns that you have to de-risk that are going to take the longest period of time if you can afford to
Do so.
Absolutely.
Th that that timeline is is is generally accurate.
Um the with the with the survey
specifically wound up happening to confirm a lot of the punches about neglected approach stuff that we had that we didn't set out to do that and had no idea what to expect.
But the survey came about as a validation to a meta approach of of trying to figure out the highest impact things to do.
We learned that alignment researchers don't think current AI safety research is on track to self-alignment in time.
They also don't think that current approaches
And yet what do people wind up putting the most time and resources into these things that are not likely to self alignment?
Like, you know
two biggest things being mechanistic interpretability and evals, which of course we think is very good to do that work and quite important.
And there are also neglected things within both of those things.
And we're working with Goodfire AI, for example, as a client doing awesome mechanistic interpretability work there.
But
And and we're very glad that that they're doing that.
Showing 301–320 of 589 · page 16 of 30
← Previous
Next →