Comment by atemerev
21 hours ago
Only if you use Kimi API directly - the censorship is done externally. The model itself talks fine about Tiananmen, you can check on Openrouter. There might be less visible biases, though.
21 hours ago
Only if you use Kimi API directly - the censorship is done externally. The model itself talks fine about Tiananmen, you can check on Openrouter. There might be less visible biases, though.
That's what I wrote? Except that it also clearly has internal bias?
> That's what I wrote?
No.
You wrote that "you won't hear about Tiananmen square from this model" and atemerev wrote that "the model itself talks fine about Tiananmen".
You wrote that "it can easily access any withheld or missing info from training data via tool calls" and atemerev wrote that "the model itself talks fine about Tiananmen".
It has internal bias too and the first comment mentions that additional censoring runs on top of the model output in the API. Did you misread or what else are you missing?
1 reply →
Everything has some sort of bias. Most text is written by those who like writing.