Sam Fieldman

DeepSeek's reasoning skills are probably particularly useful for something like this. But in my mind, particularly for academic research type tasks, the propaganda baked into the model is a non-starter. I tested out the new
DeepSeek-R1-Distill-Llama-70B-Uncensored-v2-Unbiased model yesterday. It was a very crude test, but I was quite impressed. I'm a newb over here, so take this as a light suggestion, just in case its helpful, nothing more.