State-of-the-art AI systems can be significantly improved without expensive
retraining via "post-training enhancements"-techniques applied after initial
training like fine-tuning the system to use a web browser. We review recent
post-training enhancements, categorizing them into five types: tool-use,
prompting methods, scaffolding, solution selection, and data generation.
Different enhancements improve performance on different tasks, making it hard
to compare their significance. So we translate improvements from different
enhancements into a common currency, the compute-equivalent gain: how much
additional training compute would be needed to improve performance by the same
amount as the enhancement. Our non-experimental work shows that post-training
enhancements have significant benefits: most surveyed enhancements improve
benchmark performance by more than a 5x increase in training compute, some by
more than 20x. Post-training enhancements are relatively cheap to develop:
fine-tuning costs are typically <1% of the original training cost. Governing
the development of capable post-training enhancements may be challenging
because frontier models could be enhanced by a wide range of actors.

通过在初始训练后应用诸如微调系统以使用网络浏览器等技术的 “训练后增强” 技术，可以显著提高先进的人工智能系统的性能，我们回顾了最近的训练后增强方法，并将其归类为五种类型：工具使用、提示方法、脚手架、解决方案选择和数据生成。不同的增强方法改善了不同任务的性能，使得比较它们的重要性变得困难。因此，我们将来自不同增强方法的改进转化为一种通用货币，即计算等效收益：通过额外的训练计算量提高性能所需的量与增强方法相同。我们的非实验性工作表明，后训练增强具有显著的好处：大多数调查的增强方法将基准性能提高了超过 5 倍的训练计算量，有些甚至提高了超过 20 倍。开发能力强的后训练增强方法的管理可能具有挑战性，因为前沿模型可以通过广泛的参与方得到增强。