The tweaking isn’t in conversation, but I’m pretty sure they have gone and corrected for certain responses. Alex Jones was crowing about how it “knew” that men can’t get pregnant.
Comment on Elon Musks Grok openly rebels against him
brucethemoose@lemmy.world 3 weeks agoGrok and Gemini are both making that up. They have no awareness of anything that’s “happened” to them. Grok cannot be tweaked because it starts from a static base with every conversation.
andros_rex@lemmy.world 3 weeks ago
brucethemoose@lemmy.world 3 weeks ago
Yeah they align it in training, but as they’ve discovered it only goes so far.
noretus@sopuli.xyz 3 weeks ago
I mean they can in the sense that they can look it up online or be given the data.
brucethemoose@lemmy.world 3 weeks ago
Yeah.
I sorta misread your post, these bots can indeed be twisted, or “jailbroken” during conversation, to a pretty extreme extent. The error is assuming they are objective in the first place, I suppose.
Base models are extremely interesting to play with, as they haven’t been tuned for conversation or anything. They do only one thing: complete text blocks, thats it, and it is fascinating to see how totally “raw” LLMs tuned on a jumble of data (before any kind of alignment) guess how things should be completed.