Generative AI and the problem of existential risk (2407.13365v1)

Abstract: Ever since the launch of ChatGPT, Generative AI has been a focal point for concerns about AI's perceived existential risk. Once a niche topic in AI research and philosophy, AI safety and existential risk has now entered mainstream debate among policy makers and leading foundation models developers, much to the chagrin of those who see it as a distraction from addressing more pressing nearer-term harms. This chapter aims to demystify the debate by highlighting the key worries that underpin existential risk fears in relation to generative AI, and spotlighting the key actions that governments and industry are taking thus far to helping address them.