It stands to reason that if you have access to an LLM’s training data, you can influence what’s coming out the other end of the inscrutable AI’s network. The obvious guess is that…
  • SaveTheTuaHawk@lemmy.caEnglish
    1·
    2 days ago

    It’s happening. I’ve been resampling queries every few months and the deviation of wrong to true responses is getting bigger.