High Signal Podcasts Evidence ledger
Method
Browse

Public evidence record

Nyla Worker

Published podcast speaker

Claims
10
Episodes
1
Shows
1
Named items
0

Claim ledger

What Nyla said.

5 transcript-backed records

01 / evaluation

I don't trust benchmarks, especially when the numbers are close. I'm like, okay, this is useless now because it is completely gamified, right?

“I don't trust benchmarks, especially when the numbers are close. I'm like, okay, this is useless now because it is completely gamified, right?”
Speaker
Nyla Worker
Publisher
Latent Space

02 / evaluation

The character would look at you and be like, why are you looking at me with that face? And that changes the whole flow, because right now, if you just talk to talk, it's not the same as if it sees you, it sees your reaction, and then it begins a conversation and it changes and you make a state based on that and all of that.

“The character would look at you and be like, why are you looking at me with that face? And that changes the whole flow, because right now, if you just talk to talk, it's not the same as if it sees you, it sees your reaction, and then it begins a conversation and it changes and you make a state based on that and all of that.”
Speaker
Nyla Worker
Publisher
Latent Space

03 / evaluation

Like we, we've seen papers like textbooks is all you need, right? And that is because the textbooks are starting informationally dense and it's years of a human carefully crafting like word after word after word of what they are saying.

“Like we, we've seen papers like textbooks is all you need, right? And that is because the textbooks are starting informationally dense and it's years of a human carefully crafting like word after word after word of what they are saying.”
Speaker
Nyla Worker
Publisher
Latent Space

04 / evaluation

They use samples. And obviously this is not necessarily apples to apples comparison because you need to check at the fine print as to how they are running this.

“They use samples. And obviously this is not necessarily apples to apples comparison because you need to check at the fine print as to how they are running this.”
Speaker
Nyla Worker
Publisher
Latent Space

05 / evaluation

But there were product requirements, right? And this is where inference becomes very interesting because it's not about making it the fastest, it's about meeting the human perceived latency.

“But there were product requirements, right? And this is where inference becomes very interesting because it's not about making it the fastest, it's about meeting the human perceived latency.”
Speaker
Nyla Worker
Publisher
Latent Space
Search evidence