STORY · FORSKNING_
Review of frontier post-training techniques with Finbarr Timbers
Nathan Lambert interviews Finbarr Timbers about the post-training methods used to train state-of-the-art models. The interview covers key techniques and design choices in fine-tuning large language models.
WHY IT MATTERS
Post-training is critical for getting models that work well in practice, and insights from some of the industry's best practitioners are valuable for understanding where frontier research is headed.
SOURCES
MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.