The speaker says current training around harness rollouts uses awkward, hacky methods to train language models to act within long, potentially multi-agent rollouts.

“We are now training models around harness rollouts and so there is this very awkward way of doing training over harnesses which is that we train a language model to act within a harness but like now it's like a really long maybe like multiple agent rollout that we're doing and there's like really awkward hacky ways of doing this.”