logoalt Hacker News

choppafacetoday at 3:15 AM2 repliesview on HN

“self-evolves through feedback loops”

Does this mean they distilled Claude? Sounds like what Claude Code will often do.


Replies

charcircuittoday at 3:24 AM

It's meaningless. Models have always been able to do this and this capability is strengthened during RL since being able to explore the solution space to figure something out will give it a reward.

What is important is how long it can go without requiring human intervention. Not just that it's possible to run on its own for a time.

Art9681today at 3:19 AM

Of course they did.