← Back to context

Comment by Terr_

2 months ago

I don't understand what you're trying to say here.

It sounds like "we know the LLM understood its actions... because it understood its actions when we trained it", which is circular-logic.

It's not circular. It's like saying a pizza parlor employee made a plausible pizza that tasted good, because the employee was taught how to make a good pizza during training.