app / uses
Claude
“I use Claude, not Elicit. Elicit doesn't support hiring decisions exactly yet, or I don't use it for that case.”
Public evidence record
Jungwon Byun
Published podcast speaker
- Claims
- 11
- Episodes
- 2
- Shows
- 2
- Named items
- 1
Books, apps, and tools
The evidenced stack.
Claim ledger
What Jungwon said.
5 transcript-backed records
01 / belief
I feel like there's always an explore-exploit trade-off, and you want to navigate those two thoughtfully, and sometimes you want to do one, sometimes you want to do the other. And maybe the cost of exploring has gone down a little bit, but I think there are still some things where you know you have to get it right the first time, or it's still, it's not all software engineering has literally gone to zero.
“I feel like there's always an explore-exploit trade-off, and you want to navigate those two thoughtfully, and sometimes you want to do one, sometimes you want to do the other. And maybe the cost of exploring has gone down a little bit, but I think there are still some things where you know you have to get it right the first time, or it's still, it's not all software engineering has literally gone to zero.”
- Speaker
- Jungwon Byun
- Episode
- Radically Better Reasoning: Elicit's Andreas Stuhlmüller & Jungwon Byun on World Models for Research
- Publisher
- The Cognitive Revolution
02 / belief
I think at the time, the models hadn't been trained at all to be faithful to a text.
“I think at the time, the models hadn't been trained at all to be faithful to a text.”
- Speaker
- Jungwon Byun
- Publisher
- Latent Space
03 / belief
I think one thing the longer context models changed for us is maybe a focus from breaking down tasks to breaking down the evaluation.
“I think one thing the longer context models changed for us is maybe a focus from breaking down tasks to breaking down the evaluation.”
- Speaker
- Jungwon Byun
- Publisher
- Latent Space
04 / belief
I think we also end up effectively monitoring by trying to evaluate new models as they come out.
“I think we also end up effectively monitoring by trying to evaluate new models as they come out.”
- Speaker
- Jungwon Byun
- Publisher
- Latent Space
05 / belief
I think GPT-4 unlocked tables for us, processing data from tables, which was huge.
“I think GPT-4 unlocked tables for us, processing data from tables, which was huge.”
- Speaker
- Jungwon Byun
- Publisher
- Latent Space