← Back to context

Comment by gwern

1 month ago

It is definitely not the first codebase an extensively RL-trained Claude has ever analyzed. How do you think it got so good?

3 comments

gwern

Reply

spullara 1 month ago

Meaning it has no episodic memory of any of those analyses that it has done.

gwern 1 month ago

You didn't say anything about 'episodic' and that's irrelevant to the point even if its long-term memory from training didn't count.