Settings

Theme

Show HN: Predict LLM Predictions

think-in-sync.com

3 points by flowingfocus a year ago · 2 comments

Reader

ggm a year ago

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.

  • flowingfocusOP a year ago

    Adversarial play sounds fun, I might try that out!

    The LLM we use is mistral-large-latest, we didn't do any training on the data yet

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection