Justin Johnson
speaker
345 appearances
1 recordings
1 series
first heard Nov 2025
last heard 25 Nov
Justin Johnson’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 — 1 in all, peaking in Nov 2025 with 1.
Appearances
Right.
And then like you actually lose something if you translate to this like purely tokenized representations that we use in LLMs.
Right.
Like you lose the font, you lose you lose the line breaks, you lose sort of the 2D arrangement on the page.
Um and for a lot of cases, for a lot of things, maybe that doesn't matter.
Um, but for some things it does.
Um and I I think pixels are this sort of l l more more lossless representation of what's going on in the world.
And in in some ways, a more general general representation that more matches what
what what we what we humans see as we as we navigate the world.
So so like I there's an efficiency argument to be made.
Like maybe it's not super efficient to like, you know, render your text to an image and then feed that to a vision model.
That's exactly
Yeah, I think there's different ways you could approach that problem.
Um, one is like you could try to be explicit about it and say, like, oh, I want to, you know, measure all the forces and feed those as training data to your model, right?
Then you could like sort of run a traditional physics simulation and, you know, then know all the forces in the scene and then use those as as training data to train a model that's now gonna hopefully predict those.
Or you could hope that something emerges more latently, right?
That you kind of train on something end to end and then on on a more
more general problem and then hope that somewhere some some something in in the internals of the model must learn to model something like physics in order to make the proper predictions.
Um and those are kind of the two big paradigms that we have more generally.
There you sort of get philosophical and you say that like we're trying to fit patterns too, but maybe we're trying to fit a you know, a more broad array of patterns, like over a with with a longer time horizon, a different reward function.
Showing 141–160 of 345 · page 8 of 18
← Previous
Next →