alt Hacker Newsannnd we can just 'reinvent'(*) the same techniques used to uncensor models for some time.. one step at a time.
(*) scarequotes because the LLMs that suggested these approaches have presumably been exposed to the refusal direction suppression work
annnd we can just 'reinvent'(*) the same techniques used to uncensor models for some time.. one step at a time.
(*) scarequotes because the LLMs that suggested these approaches have presumably been exposed to the refusal direction suppression work
You cannot really train on second-order effects, and if you could, then you wouldn't be able to escape third-order effects, ad infinitum.