danlaudk

techniques which increase statistical power by leveraging formal models, are particularly relevant when human interaction (or limited datapoints from scaled compute) will be more relevant to run these experiments ("field experiments"). This is because such interaction or resource is limited and statistical power can be amplified by pairing statistical techniques with formal models derived from AI internals or from models of incentivized behavior (of the human and of the AI system).  Within statistics, this long been the purvey of econometrics 

One organization that already does research in this space is Apollo research
https://www.lesswrong.com/posts/MrdFL38Zi3DwTDkKS/apollo-research-is-hiring-evals-and-interpretability

Other orgs also indicate that experiments and causal models play a productive role ( DARPA XAI  https://arxiv.org/abs/2106.05506
, and in deception too  https://arxiv.org/pdf/2307.10569.pdf

Transparency methods https://newsletter.mlsafety.org/p/ml-safety-newsletter-6 like analysing circuits

danlaudk

library(purrr)

danlaudk

import com.twitter.concurrent.Offer
import com.twitter.util.{Await, Future}
import scala.concurrent.duration._
import scala.util.Random
import scala.collection.mutable.Seq

val deadline = 3 seconds fromNow
val r = new Random()
val numPhilosophers = 3

danlaudk

-- Control.Monad.State.Strict

import Control.Applicative (liftA3)
import Control.Monad (replicateM)
import Control.Monad.Trans.State

type Stack = List[Int]
pop :: State Stack Int
pop = state $ \x ->
  case x of

danlaudk

import scala.annotation.tailrec

trait Tree[+T] {val value: T}
case class Node[+T](value: T, children:List[Tree[T]]) extends Tree[T]
case class Leaf[+T](value: T) extends Tree[T]

// returns Some(Node) or Some(Leaf) if targetValue is found, else None
// usage: use 'map' or 'foreach' to get the node from the result eg.
// getNodeInTree('g',tree).foreach{ node => println(s"Found a node: $node") }
def getNodeWhereTarget[T](target: T, tree:Tree[T]):Option[Tree[T]] = {

danlaudk

import scala.annotation.tailrec

trait Tree[+T] {val value: T}
case class Node[+T](value: T, children:List[Tree[T]]) extends Tree[T]
case class Leaf[+T](value: T) extends Tree[T]

// returns Some(Node) or Some(Leaf) if targetValue is found, else None
// usage: use 'map' or 'foreach' to get the node from the result eg.
// getNodeInTree('g',tree).foreach{ node => println(s"Found a node: $node") }
def getNodeWhereTarget[T](target: T, tree:Tree[T]):Option[Tree[T]] = {

danlaudk

Zoomable Sunburst with Labels

danlaudk

Uses of Research questions related to High School education