Learn Before
A development team is training an AI to write helpful and engaging online tutorials. The true, complex objective is to 'create content that effectively teaches users a new skill.' To make this measurable, the team chooses a surrogate objective: 'maximize the word count of the tutorial and the number of technical terms used.' Which of the following outcomes is the most likely form of misalignment to result from this choice?
0
1
Tags
Ch.5 Inference - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Evaluating Surrogate Objectives for a News-Summarizing AI
A development team is training an AI to write helpful and engaging online tutorials. The true, complex objective is to 'create content that effectively teaches users a new skill.' To make this measurable, the team chooses a surrogate objective: 'maximize the word count of the tutorial and the number of technical terms used.' Which of the following outcomes is the most likely form of misalignment to result from this choice?
Evaluating Surrogate Objectives for a Mental Well-being AI