News for hackers. Stuff that matters.

A comment on Self-Adapting Language Models. Parent comment

Re:Self-Adapting Language Models by notpushkin on Saturday June 14, 2025 @02:11AM (#44274560)
This was my first idea as well. Keep training continuously and redeploy clones after each cycle. From a layman perspective this seems reasonable :thinking:
[ Parent | on HN ]
Re:Self-Adapting Language Models by maleldil on Saturday June 14, 2025 @10:01PM (#44280071)
You can't realistically keep training the same model forever, or it will start forgetting things it knew before. The proper name for this is "catastrophic forgetting".
[ Parent | on HN ]