AI ALIGNMENT FORUM
AF

cdt
000
Message
Dialogue
Subscribe

Views my own, not my employers.

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
Base LLMs refuse too
cdt1y00

This is not an obvious continuation of the prompt to me - maybe there are just a lot more examples of explicit refusal on the internet than there are in (e.g.) real life.

Reply
Base LLMs refuse too
cdt1y00

Is there a reason to expect this kind of behaviour to appear from base models with no fine-tuning?

Reply
No posts to display.