Language Models Are Few-Shot Learners, They Just Can't Remember

Y	Hacker News new \| ask \| show \| jobs

	Language Models Are Few-Shot Learners, They Just Can't Remember (aravindjayendran.com)
	2 points by maxaravind 47 days ago

1 comments

The blog discusses a potential path to making LLMs self-referential and self-directed continual learners.

Solving continual learning is key to AGI - and we maybe close to solving it.