[–] ggm 1y 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" styleTeam models? I suppose I'm arguing for gamification with a leader board and hubristic bragging rights. [–] flowingfocus 1y 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
[–] flowingfocus 1y 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
2 comments
[ 0.28 ms ] story [ 13.5 ms ] threadSo 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.
The LLM we use is mistral-large-latest, we didn't do any training on the data yet