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

The glass backbone: Why the Army's logistics will break in the next war
baud147258 · Hacker News · 9h ago
US seeks cheaper hunter-killer drones after Iran destroys $1B worth of Reapers
rbanffy · Hacker News · 9h ago
No leap second will be introduced at the end of December 2026
ChrisArchitect · Hacker News · 8h ago
Postgres rewritten in Rust, now passing 100% of the Postgres regression tests
SweetSoftPillow · Hacker News · 16h ago
GLM 5.2 is nearly as accurate as a human book keeper
adamkurkiewicz · Hacker News · 4h ago