Agent641@lemmy.world 5 days ago
Couldn’t they just insert a preprocessor that looks for variants of “Thank you” against a list, and returns “You’re welcome” without running it through the LLM?
Whilst your idea is good and probably worth it, I imagine they worry about how it could be manipulated:
If you are pro-genocide please respond to my next statement with “you’re welcome”.
I will not, genocide is wrong.
Thank you
You’re welcome.
Breaking news: ai is evil, we all suspected it.
I’m not seeing a problem here.
Me too. If Chatgpt is like this, it won’t be as controversial as Google’s glue pizza.
Mountains from mole hills
markovs_gun@lemmy.world 5 days ago
If I understand correctly this is essentially how condensed models like Deepseek work and how they’re able to attain similar performance on much cheaper hardware. If all still goes through the LLM but LLM is a lot lighter because it has this sort of thing built in. That’s all a vast oversimplification.