Nathan Lambert
speaker
1,013 appearances
1 recordings
1 series
first heard Nov 2024
last heard Nov 2024
Nathan Lambert’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
I think being I've my background is in microelectromechanical systems and other kind of EE stuff before kind of shifting into AI.
So there is that kind of messy like
in the lab nature of like you just you're just trying to build this thing or you're like trying in that case it's like you're doing a reaction.
It's like it works or it doesn't.
In some cases.
But I think like most of it's data, it's like you kinda find hyperparameters that work and they don't really change.
Um but within that I think there's still a very high level of juice.
I think
We're doing a general model, but I still think we could fit more evals into our mix and improve performance without substantially changing the size.
I think that like the amount like you were talking about this with your recipe.
Like the amount of data that you need to target a specific eval is actually not very high.
Um and like
there's a lot more that you can do.
Th with that fact, there's a lot more post training that is not really touched.
And I think that the opportunity is high.
It's mostly about setting yourself to have an eval feedback cycle.
Like we
I talked about killing these different capabilities and that's because we didn't have a valves that we liked.
It's like I'm a hundred percent sure that we could improve them, but it's just much easier in a distributed environment where you have a source of truth, which is your evaluation.
Um, 'cause the big thing is like how do you develop character?
Showing 701–720 of 1,013 · page 36 of 51
← Previous
Next →