← Back to context Comment by bertil 1 year ago Couldn’t you gradually include more recent documents as you train? 2 comments bertil Reply changoplatanero 1 year ago You can do that but the amount of incremental data will be negligible compared to the rest of the data. Think of the knowledge cutoff more like a soft value. soulofmischief 1 year ago That makes it harder to analyze the results of training and draw conclusions for the next round.
changoplatanero 1 year ago You can do that but the amount of incremental data will be negligible compared to the rest of the data. Think of the knowledge cutoff more like a soft value.
soulofmischief 1 year ago That makes it harder to analyze the results of training and draw conclusions for the next round.
You can do that but the amount of incremental data will be negligible compared to the rest of the data. Think of the knowledge cutoff more like a soft value.
That makes it harder to analyze the results of training and draw conclusions for the next round.