5
Prompt injection in Google Translate reveals base model behaviors behind task-specific fine-tuning (www.greaterwrong.com)
submitted 9 months ago by to c/discuss@discuss.online
2 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 9 months ago

Especially interesting as translate long predates LLMs. Maybe they didn't want to publicise the change to avoid comparison with the classic algorithm.

  • permalink
  • fedilink
  • source
  • parent