High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Guillaume Lample

Published podcast speaker

Claims
9
Episodes
1
Shows
1
Named items
0

Claim ledger

What Guillaume said.

3 transcript-backed records

01 / evaluation

think initially we didn’t know, [00:23:00] we wanted completely short at the beginning of the company because, I think our study was not exactly the same as what it is today, but what we underestimated initially is the complexity of deploying this model and connecting them to everything to be sure it has access to the company knowledge on the, and it was, yeah, on, we were seeing customers struggling with this, but it was even, that was three years ago and no, things are much more complicated because now you don’t just have, text on SFT on a simple instruction following.

“think initially we didn’t know, [00:23:00] we wanted completely short at the beginning of the company because, I think our study was not exactly the same as what it is today, but what we underestimated initially is the complexity of deploying this model and connecting them to everything to be sure it has access to the company knowledge on the, and it was, yeah, on, we were seeing customers struggling with this, but it was even, that was three years ago and no, things are much more complicated because now you don’t just have, text on SFT on a simple instruction following.”
Publisher
Latent Space

02 / evaluation

No I think the way it works is that we are the, we are prioritizing together, I think, what are the most important features because there are many things we can do [00:09:00] in audio.

“No I think the way it works is that we are the, we are prioritizing together, I think, what are the most important features because there are many things we can do [00:09:00] in audio.”
Publisher
Latent Space

03 / evaluation

I think we started too early before doing reasoning without LMD is very hard, especially when you work with formal systems because the amount of data you have is negligible.

“I think we started too early before doing reasoning without LMD is very hard, especially when you work with formal systems because the amount of data you have is negligible.”
Publisher
Latent Space
Search evidence