idea: adversarial reinforcement learning of LLMs via gaslighting

Reply to this note

Please Login to reply.

Discussion

What’s an LLM ?

Large language model ?

Definitely not large language model

Lying Liberal Media?

Then what is it? 🤣

What are you talking about

I have no idea :) forget it :D

its too easy to gaslight, i guess humans need this too 😂

Then you add the law of large numbers…

😂

Gaslighting Adversarial Network

Imagine how based LLMs facts would become once they start getting trained on nostr data... Free and open to scrape.

Is this the real life?