tl;dr Argumate on Tumblr found you can sometimes access the base model behind Google Translate via prompt injection. The result replicates for me, and specific responses indicate that (1) Google Translate is running an instruction-following LLM that self-identifies as such, (2) task-specific fine-tuning (or whatever Google did instead) does not create robust boundaries between "content to process" and "instructions to follow," and (3) when accessed outside its chat/assistant context, the model defaults to affirming consciousness and emotional states because of course it does.
  • m_‮f@discuss.onlineOPMEnglish
    6·
    18 hours ago

    Interesting to see that Google Translate is using an LLM under the hood. Not surprising, given how good they are are language tasks, but kind of surprising that it’s not officially acknowledged anywhere.

    • CameronDev
      5·
      15 hours ago

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