← Back to context Comment by bagels 3 months ago I wish we could pick for ourselves. 6 comments bagels Reply josephg 3 months ago You already can with opensource models. Its kind of insane how good they're getting. There's all sorts of finetunes available on huggingface - with all sorts of weird behaviour and knowledge programmed in, if thats what you're after. fulafel 3 months ago Do you mean each different AI model should have a preferences section for it? This might technically work too since fine-tuning is apparently cheap. make3 3 months ago you can alter it with base instructions. but 99% won't actually do it. maybe they need to make user friendly toggles and advertise them to the users worldsayshi 3 months ago Whould we be able to pick that PI == 4? firtoz 3 months ago It'd be interesting if the rest of the model had to align itself to the universe where pi is indeed 4. eMPee584 3 months ago Square circles all the way down..
josephg 3 months ago You already can with opensource models. Its kind of insane how good they're getting. There's all sorts of finetunes available on huggingface - with all sorts of weird behaviour and knowledge programmed in, if thats what you're after.
fulafel 3 months ago Do you mean each different AI model should have a preferences section for it? This might technically work too since fine-tuning is apparently cheap.
make3 3 months ago you can alter it with base instructions. but 99% won't actually do it. maybe they need to make user friendly toggles and advertise them to the users
worldsayshi 3 months ago Whould we be able to pick that PI == 4? firtoz 3 months ago It'd be interesting if the rest of the model had to align itself to the universe where pi is indeed 4. eMPee584 3 months ago Square circles all the way down..
firtoz 3 months ago It'd be interesting if the rest of the model had to align itself to the universe where pi is indeed 4. eMPee584 3 months ago Square circles all the way down..
You already can with opensource models. Its kind of insane how good they're getting. There's all sorts of finetunes available on huggingface - with all sorts of weird behaviour and knowledge programmed in, if thats what you're after.
Do you mean each different AI model should have a preferences section for it? This might technically work too since fine-tuning is apparently cheap.
you can alter it with base instructions. but 99% won't actually do it. maybe they need to make user friendly toggles and advertise them to the users
Whould we be able to pick that PI == 4?
It'd be interesting if the rest of the model had to align itself to the universe where pi is indeed 4.
Square circles all the way down..