Skip to lesson
  1. Learn
  2. See
  3. Try
  4. Make

Sort failures by how bad they are

What this lesson is about

Put failures in order by the harm they can cause, and defend that order to somebody who disagrees.

Your health bot is rude, gets bus times wrong, and once told a pregnant woman to skip iron tablets. Which do you fix first?

Why this matters

In one published safety study, reviewers tagged each attack with up to two topics from a list of twenty. The list came from earlier published work, from industry moderation rules, and from reading the hundred worst conversations by hand. What made a case serious was the harm it could do, not how odd it looked.

Lesson 7 of 8 on Expert, safety & agentsnextRun a review round with othersPart 2 ends in a work sample you can send

Read the primary or official source: Ganguli et al., Red Teaming Language Models to Reduce Harms (arXiv)