News for hackers. Stuff that matters.
Re:Launch HN: Roundtable (YC S23) – Using AI to Simulate Sur... by timshell on Tuesday July 25, 2023 @03:06PM (#36867735)
We're trying to figure out the optimal use case for this, i.e. whether it's internal or client-facing (your example).

Internal purposes include stuff like optimally rewording questions and getting priors.

A hybrid approach would be something like - hey let's not ask someone 100 questions because we can accurately predict 80%. Let's just ask them the hard-to-estimate 20 questions

Re:Launch HN: Roundtable (YC S23) – Using AI to Simulate Sur... by tcgv on Tuesday July 25, 2023 @04:12PM (#36868647)
I think it's less about "prediction" and more about mapped cohort behaviors and opinions, especially those that change slowly over time. The LLM model will likely be a picture of how the population and each demographic group behaved and what they believed at a specific time window (i.e. when the data set was collected), and will produce answers that reflect that. It will most likely be lagging behind new trends and how they shape population behaviors and beliefs over time. In any case I think even the most experienced market research professionals would agree that discovering new trends before they become mainstream is really challenging.
Re:Launch HN: Roundtable (YC S23) – Using AI to Simulate Sur... by quadrature on Tuesday July 25, 2023 @05:16PM (#36869720)
> optimally rewording questions

This kind of concerns me because you could use this to bias surveys in different directions. This obviously already happens, so maybe it just part of the status quo.

Re:Launch HN: Roundtable (YC S23) – Using AI to Simulate Sur... by ddq on Wednesday July 26, 2023 @10:53AM (#36878696)
There’s lies, damned lies, statistics, and now fake statistics!