from Hacker News

Show HN: Predict LLM Predictions

by flowingfocus on 2/8/25, 7:14 AM with 2 comments

• by ggm on 2/8/25, 7:17 AM

  Adversarial play might be interesting. I'm assuming the goal here is to use the feedback as training input, fitness to expectations and like.

  So a random chance of a bad actor adversary? Or high scores for lying? "The traitor" style

  Team models? I suppose I'm arguing for gamification with a leader board and hubristic bragging rights.