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)→
More from AGI Musings
- Rep. Whitesides calls 30-day AI slowdown; Grady Booch fires back over basic security failures — PolarBearby · 2026-09-19
- A Country of Geniuses at Human Speed vs. Light Speed Is a Different World — akyurekekin · 2026-09-19
- If AI can do the assignment, does it still prove learning? An uncomfortable education question — PolarBearby · 2026-09-19
- binarybits pushes back: consumers won't buy the stuff AI automation could produce — binarybits · 2026-09-19
- Pause crowd might have it backwards: podcast debates whether halting AI is the harmful choice — thursdai_pod · 2026-09-19
- Back-of-envelope math says air-gapped weight exfiltration via CPU temps would take 15,000 years — anshulkundaje · 2026-09-19