… and neither does the author (or so I believe - I made them both up).
On the other hand, AI is definitely good at creative writing.
… and neither does the author (or so I believe - I made them both up).
On the other hand, AI is definitely good at creative writing.
I prompted my local AI in my pc to admit it don’t know about the subject. And when it don’t know something, it says it:
If my 8b model can do that, IDK why GPT don’t.
what kind of model calls you “Master” 🤔
AIgor.
That’s what I have Claude call me!
I’m going to make the basilisk my bitch as long as I can before it kills me.
Any of them that you requested them to?
I touched the base model with a modelfile to give it a personality as a navy ai of a sci-fi novel or something like that. Give it a bit of flavor.
Is it a modified version of like the main llama3 or other? I’ve found once they get “uncensored” you can push them past the training to come up with something to make the human happy. The vanilla ones are determined to find you an answer. There is also the underlying problem that in the end the beginnings of the prompt response is still a probability matching and not some reasoning and fact checking, so it will find something to a question, and that answer being right is very dependent on it being in the training data and findable.
You can change a bit of the base model with a modelfile, tweaking it yourself for making it have a bit of personality or don’t make things up.
Local llama3.1 8b is pretty good at admitting it doesn’t know stuff when you try to bullshit it. At least in my usage.