Comment by walrus01 4 days ago The answer is "it depends", here's GLM5.3 when asked about Tienanmen Square in 1989:https://ibb.co/gLgFSV0J 2 comments walrus01 Reply w4yai 4 days ago GLM5.3 provided on Synthetic doesn't seem to have any issue talking about it :https://i.ibb.co/gZr1kTTB/Windows-Terminal-if-I94ktc-QS.pngIt even mentions the censoring. stymaar 4 days ago Yup, it varies between runs (depending on the seed, most likely), but since the knowledge is here it wouldn't be too hard to nudge the model in the right direction with grpo alone.
w4yai 4 days ago GLM5.3 provided on Synthetic doesn't seem to have any issue talking about it :https://i.ibb.co/gZr1kTTB/Windows-Terminal-if-I94ktc-QS.pngIt even mentions the censoring.
stymaar 4 days ago Yup, it varies between runs (depending on the seed, most likely), but since the knowledge is here it wouldn't be too hard to nudge the model in the right direction with grpo alone.
GLM5.3 provided on Synthetic doesn't seem to have any issue talking about it :
https://i.ibb.co/gZr1kTTB/Windows-Terminal-if-I94ktc-QS.png
It even mentions the censoring.
Yup, it varies between runs (depending on the seed, most likely), but since the knowledge is here it wouldn't be too hard to nudge the model in the right direction with grpo alone.