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?
The issue is not what's missing - it's what you wrote that is in direct contradiction with what atemerev wrote like the bit about "missing info from training data".
But sure, if when you wrote "you won't hear about Tiananmen square from this model" you meant "the model itself talks fine about Tiananmen" then that's exactly what you wrote.
> 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?
The issue is not what's missing - it's what you wrote that is in direct contradiction with what atemerev wrote like the bit about "missing info from training data".
But sure, if when you wrote "you won't hear about Tiananmen square from this model" you meant "the model itself talks fine about Tiananmen" then that's exactly what you wrote.
Everything has some sort of bias. Most text is written by those who like writing.