Rogue ASI Can't Stay Aligned to Itself

·LessWrong··

In a world where rogue ASI can form a singleton, could it really widely deploy an agent fleet across the world(let alone onto other stellar bodies) without running the risk of an agent going rogue?AI capable of conducting a hostile takeover is type 1 technology: a low-cost, accessible means of bringing about global catastrophe. Notably, the vulnerable world typology classifies technologies, not particular instances of a given technology. After all, the thing that makes type 1 technology so dange...

Read full article →

Related Articles

Coconut oil jet fuel matches kerosene's efficiency in engine tests
mdp2021 · Hacker News · 8h ago
Slovakia finds Russian backdoor in traffic speed cameras
dredmorbius · Hacker News · 9h ago
GLM-5.3 (open-weight) beat Anthropic/OpenAI models – for 1/5 the cost
ed-is-ai · Hacker News · 7h ago
There's no reason for software to be slow anymore
Jach · Hacker News · 1d ago
How Complex Systems Fail (1998)
shortcrct · Hacker News · 9h ago