← Back to context Comment by howdareme 8 hours ago They are not training a whole model in a matter of days 3 comments howdareme Reply johnnienaked 1 hour ago They don't need to train a whole model. They can feed it new information and fine tune it. irthomasthomas 4 hours ago They where working on the problem for a year using codex. xdavidliu 5 hours ago pretraining is months but they can totally fine tune in a few days
johnnienaked 1 hour ago They don't need to train a whole model. They can feed it new information and fine tune it.
They don't need to train a whole model. They can feed it new information and fine tune it.
They where working on the problem for a year using codex.
pretraining is months but they can totally fine tune in a few days