> Most approaches in this space generate thousands of individual simulated personas, ask each one your question, and aggregate the answers. We think that's backwards. You're creating artificial noise and then averaging it out. The noise doesn't add information. We skip the personas entirely and estimate the aggregate directly.
Whoever it was who bet me 20 Euros that we already are already living in a dystopia, my opinion to the contrary notwithstanding, i owe you some money.
> Most approaches in this space generate thousands of individual simulated personas, ask each one your question, and aggregate the answers. We think that's backwards. You're creating artificial noise and then averaging it out. The noise doesn't add information. We skip the personas entirely and estimate the aggregate directly.
Whoever it was who bet me 20 Euros that we already are already living in a dystopia, my opinion to the contrary notwithstanding, i owe you some money.
[dead]
Talk about the target becoming the measure...
"What our firm offers is re-alignment of your market data with the simulation"
[dead]
[dead]