High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

George Cameron

Published podcast speaker

Claims
7
Episodes
1
Shows
1
Named items
0

Claim ledger

What George said.

7 transcript-backed records

01 / belief

I think our view is that hallucination rate makes sense in this context where it’s around knowledge, but in many cases, people want the models to hallucinate, to have a go.

“I think our view is that hallucination rate makes sense in this context where it’s around knowledge, but in many cases, people want the models to hallucinate, to have a go.”
Speaker
George Cameron
Publisher
Latent Space

02 / belief

Our accuracy, benchmark as part of a omniscience, it’s very correlated with total. It’s not correlated with, with active, uh, parameters, which I think is very at all, which is very, very interesting.

“Our accuracy, benchmark as part of a omniscience, it’s very correlated with total. It’s not correlated with, with active, uh, parameters, which I think is very at all, which is very, very interesting.”
Speaker
George Cameron
Publisher
Latent Space

05 / evaluation

One extra, um, point regarding, um, GDP Val AA is that on the basis of the overperformance of the models compared to the chatbots turns out, we realized that, oh, like our reference harness that we built actually white works quite well on like gen generalist agentic tasks.

“One extra, um, point regarding, um, GDP Val AA is that on the basis of the overperformance of the models compared to the chatbots turns out, we realized that, oh, like our reference harness that we built actually white works quite well on like gen generalist agentic tasks.”
Speaker
George Cameron
Publisher
Latent Space

06 / observation

Interestingly in Tal, um, Tal2Bench Telecom, it’s cheaper to run, you know, on a per token basis, more expensive models like a GBD5 compared to some smaller open source models, because the, um, some of the GBD5, for instance, uh, got to the answer faster.

“Interestingly in Tal, um, Tal2Bench Telecom, it’s cheaper to run, you know, on a per token basis, more expensive models like a GBD5 compared to some smaller open source models, because the, um, some of the GBD5, for instance, uh, got to the answer faster.”
Speaker
George Cameron
Publisher
Latent Space
Search evidence