Defending Alignment: A Commentary On ‘AI Survival Stories’
Year: 2025
Type: article
Abstract: This paper criticises the claims of Cappelen et. al (2025) to have provided “significant challenges” to the claim that humanity will not be destroyed by AI. Specifically, I claim that they fail to substantiate their claims that extremely powerful AI systems of the future will engage in destructive conflict with humanity.
Source: Philosophy of AI
Author: Svarc, Rory
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W7117307238
FWCI:
Cites:
Cited by:
Related to: