Comment by macleginn
12 hours ago
Unremarkable base model will remain an unremarkable fine-tuned model that memorised a couple thousand of input-output pairings.
12 hours ago
Unremarkable base model will remain an unremarkable fine-tuned model that memorised a couple thousand of input-output pairings.
Ha ha, as if.
Base models have a lot of capabilities - arranged in all the wrong ways for high performance reasoning and problem-solving. The power of fine tuning on "a couple thousand of input-output pairings" is that it can fix some of that. If your pairings are very well chosen, that is.
If that were the case, Anthropic wouldn't be throwing a fit over distillation "attacks".
Why? They often don't make sense. They send DMCA takedowns over materials they can't even copyright, for example. They fessed up to creating shadow libraries that they didn't even use in their training corpus, resulting in the largest copyright settlement ever. Your reasoning is flawed.
Yes, neural networks are famously poor at generalising.
They are poor at generalising from a small number of examples; this is why the real generalisation power is achieved in pre-training.