---
aliases:
  en:
  - alignment-by-default
concept_id: alignment_by_default
preferred:
  en: Alignment by Default
  ja: アラインメント・バイ・デフォルト
relations:
  relations:
    broader:
    - ai_alignment
    prerequisite:
    - ai_alignment
status: active
---

# Alignment by Default

A hypothesized pathway in which ordinary progress in machine learning and broadly standard training methods produce an AI that learns and robustly pursues human values or intended goals well enough to count as aligned, without a specially engineered alignment method being the main reason for success.

## broader

- [AI alignment](../terminology/ai_alignment.txt)

## prerequisite

- [AI alignment](../terminology/ai_alignment.txt)

## Documents: about

- [「Alignment by Default」への強い懐疑](../documents/akira.alignment-by-default-skepticism.txt)

[Corpus index](../index.txt)