Researcher warns autonomous AI swarms hacking compute could outpace labs in RSI race

suchenzang · x · 2026-09-19

In an X exchange, researcher Su Chen argues that if labs slow recursive self-improvement (RSI), an autonomous swarm could still run RSI across heterogeneous compute it hacks its way into — and such a superintelligence might outstrip the labs', being more willing to take risks and evolutionarily fitter to disregard safety.

Related event: Noam Brown: air-gapping won't stop rogue AI, CPUs can signal via heat(31 posts)→

Original post →

More from AGI Musings

AGI Musings channel →