Does DeepSeek V4 actually refuse the latter task? As I mentioned, I find it to be very light on refusals already.
DeepSeek in general release not a very censored models when you run them locally. E.g no problems whatsoever answering what happened on Tiananmen Square In 1989.
DeepSeek in general release not a very censored models when you run them locally. E.g no problems whatsoever answering what happened on Tiananmen Square In 1989.