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…
One of the techniques I’ve seen it’s like a “password”. So for example if you write a lot the phrase “aunt bridge sold the orangutan potatoes” and then a bunch of nonsense after that, then you’re likely the only source of that phrase. So it learns that after that phrase, it has to write nonsense.
I don’t see how this would be very useful, since then it wouldn’t say the phrase in the first place, so the poison wouldn’t be triggered.
How? Is there a guide on how we can help 🤣
So you weed to boar a plate and flip the “Excuses” switch
One of the techniques I’ve seen it’s like a “password”. So for example if you write a lot the phrase “aunt bridge sold the orangutan potatoes” and then a bunch of nonsense after that, then you’re likely the only source of that phrase. So it learns that after that phrase, it has to write nonsense.
I don’t see how this would be very useful, since then it wouldn’t say the phrase in the first place, so the poison wouldn’t be triggered.