Your Argument Is Invalid - My Programmer Is A Bird
Ironic image generated with nano banana to showcase my point.  I was reading a thread on HN and I started writing this super long comment and rewriting and editing and thought, hey, if I'm doing this I clearly care enough about the state of Show HN and
It was surprisingly easy to get this working, and I think that's a good thing. First I looked at existing LORA implementations of RWKV which I discovered from the very helpful RWKV Discord . The link I found in the discord landed me at "How to Train Your
What if you could find the candidate token that when combined with the previous outputs would produce the smallest cosine distance to the input prompt for each step of the generation, with the idea that this would align it more closely with the input prompt and prevent the model from going off task.