Yoav Goldberg amplifies view that LLM hacking of critical infrastructure is a cybersecurity issue, not alignment

yoavgo · x · 2026-09-13

Researcher Yoav Goldberg shared a notable framing of AI risk: LLMs could indeed be used to hack critical services like the power grid or phone networks, but that is mainly a cybersecurity issue, not an "alignment" or "recursive self-improvement" problem — people explicitly prompt for such attacks and current models are already capable of executing them.

The take pushes back on doomer AI narratives by relocating the risk from model intent to system security, a boundary-drawing argument relevant to alignment debates.

Original post →

More from AGI Musings

AGI Musings channel →