other / built
Avalon
“At that time we built Avalon as a research environment to help us learn particular things.”
Public evidence record
Kanjun Qiu
Published podcast speaker
- Claims
- 20
- Episodes
- 1
- Shows
- 1
- Named items
- 1
Books, apps, and tools
The evidenced stack.
Claim ledger
What Kanjun said.
4 transcript-backed records
01 / preference
On the theoretical side, we like really believe in like deeply understanding, like when we actually fine tune on individual examples, like what's going on, when we're pre-training, what's going on, like debugging tools for these agents to understand like what's going on.
“On the theoretical side, we like really believe in like deeply understanding, like when we actually fine tune on individual examples, like what's going on, when we're pre-training, what's going on, like debugging tools for these agents to understand like what's going on.”
- Speaker
- Kanjun Qiu
- Publisher
- Latent Space
02 / preference
We built Avalon mostly because we couldn't use Minecraft very well to like learn the things we wanted.
“We built Avalon mostly because we couldn't use Minecraft very well to like learn the things we wanted.”
- Speaker
- Kanjun Qiu
- Publisher
- Latent Space
03 / preference
All of them? I think the only successful agents are the ones that do really small things.
“All of them? I think the only successful agents are the ones that do really small things.”
- Speaker
- Kanjun Qiu
- Publisher
- Latent Space
04 / preference
I like to think about team members as creative agents, because most companies, they think of their people as assets and they're very proud of this.
“I like to think about team members as creative agents, because most companies, they think of their people as assets and they're very proud of this.”
- Speaker
- Kanjun Qiu
- Publisher
- Latent Space