27
Remember when we had to train models on our own machines?
Back in 2018 I was running LSTM text generators on my laptop and it would take 12 hours just to see if something worked. Now I just paste a prompt into a cloud API and get results in seconds. Has anyone else found themselves forgetting how much work the old workflow actually was?
2 comments
Log in to join the discussion
Log In2 Comments
murray.cole21d ago
Honest to god I still keep an old GPU around for local testing before I burn API credits.
0
gonzalez.rowan21d agoTop Commenter
Bro fr local testing is way better for catching stupid mistakes before the money flies out
4