Jennifer Li
speaker
607 appearances
7 recordings
1 series
first heard Dec 2024
last heard 4d ago
Jennifer Li’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 4 in all, peaking in Sep 2026 with 2.
Appearances
I guess what is stunning to me is there is like magnitude lower cost and also much faster.
I think it was like thirty five X speed up.
Compared to
Well at the ELO score you didn't really sacrifice quality.
So yeah, just maybe it revealed a bit more of the secret sauce behind of is this more of the type of system work you have done?
Like did you have to do like model architecture change?
Is it system work that really brought down the cost and latency?
And how about like the next generation of chips like G B two hundred fits into the whole story?
Story.
Maybe this is a detailful question, like is the model being served on single GPU or like It is
It is run
And do you think there will be more efficiency gains in there that you can either, you know, optimize more of the steps in between by sacrificing maybe some of the um like narrow down the user experiences, let's say like the different type of inputs and outputs or like
as you're thinking of parallelism like i is there more juice to squeeze, maybe that's the that's
Yeah, we
Were you surprised by the speed up and the gain you could get from post training this model?
Like like I I I saw it as a little bit of a surprise that like one day I think it was a Saturday you'll launch the model and the Sunday people put it on Twitch, it become a real time model.
Like what I think that's the interesting part of like when you're reading.
Interesting part of like when you
I guess well you're taking by surprise the the real time uh use case that came out of it or or what are some examples that you think this model has like unlocked of the experiences the prior models could
Yeah the experience.
Showing 21–40 of 607 · page 2 of 31
← Previous
Next →