- cross-posted to:
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- cross-posted to:
- [email protected]
- [email protected]
- [email protected]
- [email protected]
Basically: you ask for poems forever, and LLMs start regurgitating training data:
My fun guesswork here is that I don’t think the neural net weights change during querying, only during training. Otherwise the models could be permanently damaged by users.
The neural net doesn’t change of course, but previous text is used as context for the next generation.