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 I'm gonna give a I'm gonna I'm signed up for some NEREPS talk on like AI engineers and I'm gonna try to figure out a worldview on like
how to come up with these RL verifiers for different tasks.
Cause I do think if you have a verifier and the distribution matches your task, like this RL stuff will just kinda work.
And it's kinda it would be really interesting to see more engineery and less researchy people try to adapt this and just take it.
And we have early days of what we call like LLM Gym or like an open source repo where you can like add different constraints and then just do RL on it and take the model and like you could add these domain you're essentially adding domains for RL and language models.
So I think that's kind of the newest frontier where some of these like SFT single domain, few domain, it's like
you could try it and you could see and it's not that interesting, but like
If we can unlock RL with verifiers for so many different niches, it'll be really like a
the next moment in this kind of like fine tuning specific language models narrative.
Yeah, verify.
Judge it,
Yeah, we have I don't I don't know if I have the energy for the whole multimodal discussion, but there are definitely different guidelines as you go multimodal I think.
Preferences are more powerful in things like images, audio, video, because our intuitions, especially human preferences, are just intuitively much more expressive.
um than in text.
So a lot of things they're saying are very like text and
In that way, like.
capability in a very narrow sense.
probably do like um detectors of different types of objects if you like you're saying, like make sure if they have a prompt, you can do a detector to make sure that certain noun or entities in the prompt are in the image.
And I bet you could have a like that is a way of doing precise instruction following for images.
And I wouldn't be surprised if it's already done.
Showing 921–940 of 1,013 · page 47 of 51
← Previous
Next →