High Signal Podcasts Evidence ledger
Method
Browse

Public evidence record

Petar Velichkovich

Published podcast speaker

Claims
4
Episodes
1
Shows
1
Named items
0

Claim ledger

What Petar said.

2 transcript-backed records

01 / evaluation

We are working in this high dimensional space, which is not necessarily easily interpretable or composable because you have no easy way of saying, for example, in in theoretical computer science, if you want to compose 2 algorithms, you're working with them in a very abstract space, which means that, you know, you can easily reason about stitching the output of 1 to the input of another, whereas you cannot make that easy of a claim about latent spaces of 2 neural networks.

“We are working in this high dimensional space, which is not necessarily easily interpretable or composable because you have no easy way of saying, for example, in in theoretical computer science, if you want to compose 2 algorithms, you're working with them in a very abstract space, which means that, you know, you can easily reason about stitching the output of 1 to the input of another, whereas you cannot make that easy of a claim about latent spaces of 2 neural networks.”
Publisher
Machine Learning Street Talk

02 / evaluation

When you think about all of the big scientific advances that were done with large language models, for example, up to this date, I would argue most of the ones I'm personally familiar with are a result of a careful combination of a large language model and an algorithmic procedure in the background, which actually makes sure to give it robustness properties.

“When you think about all of the big scientific advances that were done with large language models, for example, up to this date, I would argue most of the ones I'm personally familiar with are a result of a careful combination of a large language model and an algorithmic procedure in the background, which actually makes sure to give it robustness properties.”
Publisher
Machine Learning Street Talk
Search evidence