pull down to refresh

I was testing the tricks outlined in #1206827 on Gemma3 yesterday to make it say stuff it's explicitly trained to not do during SFT, and honestly, Google made it tight! I couldn't get it to say anything off at all. Also not with the leetspeak trick.
But this also means that making it ignore (c) sources will be much harder on tightly instructed models.
So, what's gonna happen to the models that are already trained and up for grabs?
reply
Well... the genie is out of the bottle, good luck getting it back in.
reply
that's what I thought. So it's pretty much just the big tech companies that gotta comply.
reply
They don't have to comply with anything really. They just gotta pay up.
reply