We’ve demonstrated reward learning from human preferences on 2 kinds of natural language tasks, stylistic continuation and summarization. Our results are mixed: for continuation we achieve good results with very few samples, but our summarization models are only “smart copiers”: they copy from the input text but skip over irrelevant preamble. The advantage of smart copying is truthfulness: the 0-shot and supervised models produce natural, plausible-looking summaries that are often lies. We believe the limiting factor in our experiments is data quality exacerbated by the online data collection setting, and plan to use batched data collection in the future.

• Uncategorized