High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Peter Robicheaux

Published podcast speaker

Claims
3
Episodes
1
Shows
1
Named items
0

Claim ledger

What Peter said.

3 transcript-backed records

01 / evaluation

See these details. So it hypothesizes that models that have been initialized with, with Clip as their vision encoder, they don't have fine grained details and the, the features extracted using Clip because Clip sort of doesn't need to find these fine grained [00:22:00] details to do its job correctly, which is just to match captions and images, right?

“See these details. So it hypothesizes that models that have been initialized with, with Clip as their vision encoder, they don't have fine grained details and the, the features extracted using Clip because Clip sort of doesn't need to find these fine grained [00:22:00] details to do its job correctly, which is just to match captions and images, right?”
Publisher
Latent Space

02 / prediction

You know, if we just keep bumping the parameter count and increasing the example scene, which is the, the, the line of thinking for language models, then it'll keep getting better. So how does it actually do at finding, oh, it also improves with resolution, which you would expect for a model that This is the ImageNet classification accuracy, but yeah, it does better if you increase the resolution, which means that it's actually leveraging and finding fine grained visual features.

“You know, if we just keep bumping the parameter count and increasing the example scene, which is the, the, the line of thinking for language models, then it'll keep getting better. So how does it actually do at finding, oh, it also improves with resolution, which you would expect for a model that This is the ImageNet classification accuracy, but yeah, it does better if you increase the resolution, which means that it's actually leveraging and finding fine grained visual features.”
Publisher
Latent Space

03 / evaluation

Lava is, interestingly, extremely negatively correlated with this dataset. It does much, much, much, much worse [00:24:00] than random guessing, which means that this process has done a very good job of identifying hard images for, for Lava, specifically.

“Lava is, interestingly, extremely negatively correlated with this dataset. It does much, much, much, much worse [00:24:00] than random guessing, which means that this process has done a very good job of identifying hard images for, for Lava, specifically.”
Publisher
Latent Space
Search evidence