Work

Unpredictability of AI Alignment Is Not Always Bad for AI Safety

Year: 2025

Type: preprint

Source: PhilSci-Archive (University of Pittsburgh)

Authors: Spelda, Petr, Stritecky, Vit

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W7110706733

Cites:

Cited by:

Related to: 10