Kristin Tynski
speaker
493 appearances
3 recordings
1 series
first heard Mar 2026
last heard 26 Mar
Kristin Tynski’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 — 3 in all, peaking in Mar 2026 with 3.
Appearances
So a transformer is basically like a giant matrix.
You can think of it like a spreadsheet.
It's um the weights are in each individual cell.
And every time that the training is done or each pass of training is done, every single weight is updated.
So it's an incredibly um computationally dense.
thing and for that reason it's also very uh it's a it's a huge energy suck, right?
So like
Talking about building massive data centers that are requiring even their own power plants.
Um, the future of transformers in terms of scaling them is sort of hitting an upper limit.
Um
we know that they they scale in a quadratic way.
So
the more parameters you have and the more training you do, the more compute you need, um in in a in a really exponential way.
So we're we're sort of hitting the upper limit and and I think that's that's really uh what's going to require us to to find this new paradigm.
Yeah, so it
When we get these new architectures, the primary thing that's going to be solved is continual learning.
So right now, transformers need to be trained and then they can run inference and and you get an answer, but they're not learning as you're working with them.
They were trained once and then they're doing inference.
The next generation of models will be continual learners.
So
Showing 41–60 of 493 · page 3 of 25
← Previous
Next →