← Back to context Comment by bertil 13 days ago Couldn’t you gradually include more recent documents as you train? 2 comments bertil Reply changoplatanero 13 days 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 13 days ago That makes it harder to analyze the results of training and draw conclusions for the next round.
changoplatanero 13 days 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 13 days 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.