pretraining is an elegant science, done by mathematicians who sit in cold rooms writing optimization theory on blackboards, engineers with total absorb of distributed systems of titanic scale posttraining is hair raising cowboy research where people drinking a lot of diet coke yell new hyperparameters to try at each other across the room. it’s doing too many tables! the vibes are getting worse, turn down the knob! checkpoint gpt-9-final-v320-restart4 is calling me names! the goose is loose