2 papers
cs.AI2026
AI Survival Stories: a Taxonomic Analysis of AI Existential Risk
Herman Cappelen, Simon Goldstein, John Hawthorne
Since the release of ChatGPT, there has been a lot of debate about whether AI systems pose an existential risk to humanity. This paper develops a general framework for thinking abo…
cs.AI2024
AI Safety: A Climb To Armageddon?
Herman Cappelen, Josh Dever, John Hawthorne
This paper presents an argument that certain AI safety measures, rather than mitigating existential risk, may instead exacerbate it. Under certain key assumptions - the inevitabili…