|
|
|
|
|
|
by gpderetta
930 days ago
|
|
|
To be more constructive, I agree that personal spam/nom-spam decisions should not be used to train a general model, at least not without a significant signal from multiple users. Possibly users should be matched to models according to their behaviour. But the onus should be on the model builders not on the final user. |
|
|