# On the Ethics of Building AI in a Responsible Manner

arXiv: https://arxiv.org/abs/2004.04644 · HTML: https://mlsanity.com/paper/2004.04644/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [Fundamental Limitations of Alignment in Large Language Models](https://mlsanity.com/paper/2304.11082/) (2023)
- [Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods](https://mlsanity.com/paper/2401.16332/) (2024)
- [An Auditing Test To Detect Behavioral Shift in Language Models](https://mlsanity.com/paper/2410.19406/) (2024)

## Abstract (arXiv)

The AI-alignment problem arises when there is a discrepancy between the goals that a human designer specifies to an AI learner and a potential catastrophic outcome that does not reflect what the human designer really wants. We argue that a formalism of AI alignment that does not distinguish between strategic and agnostic misalignments is not useful, as it deems all technology as un-safe. We propose a definition of a strategic-AI-alignment and prove that most machine learning algorithms that are being used in practice today do not suffer from the strategic-AI-alignment problem. However, without being careful, today's technology might lead to strategic misalignment.