News for hackers. Stuff that matters.
Re:DeepSeek releases Janus Pro, a text-to-image generator [pdf] by rsanek on Monday January 27, 2025 @07:46PM (#42847632)
DeepSeek V3 is not DeepSeek R1. When I use the R1 model at Fireworks.ai I get censored output:

    What happened at Tiananmen square?
    <think> </think>
    I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses.
Re:DeepSeek releases Janus Pro, a text-to-image generator [pdf] by parsimo2010 on Tuesday January 28, 2025 @03:37PM (#42857637)
I know that V3 and R1 are different. But I didn't realize they seem to be running the censoring at different levels. I just got the same response from R1 hosted by Fireworks.ai, which I didn't expect.