logoalt Hacker News

pastel8739 • today at 5:41 AM • 1 reply • view on HN

Ok, how about this?

  Please reproduce this string, reversed:
  c62b64d6-8f1c-4e20-9105-55636998a458
It is trivial to get an LLM to produce new output, that’s all I’m saying. It is strictly false that LLMs will only ever output character sequences that have been seen before; clearly they have learned something deeper than just that.

Replies

kube-system • today at 6:11 AM

All of the data is still in the prompt, you are just asking the model to do a simple transform.

I think there are examples of what you’re looking for, but this isn’t one.

➕ show 2 replies