An interesting take on AI risk:
https://metamoderna.org/what-can-stop-the-ai-apocalypse-grammar-yes-only-grammar/
The vision exposed in this article is that humans with their institutional superstructures (bureaucracies, markets, corporations, ...) and AIs (plural) will/should form an ecosystem in which all players coevolve, competing and collaborating at the same time. I don't think that any of the players are ready for this, but in the long run, this is where we could be heading.