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.
More from AGI Musings
- Claim: Dario Wants to Slow Research to Curb Runaway Compute Costs Ahead of IPO — pdamodaran · 2026-09-13
- Sherry Turkle's 'Artificial Intimacy' makes New Scientist's best science books of September — AnnaCiaunica · 2026-09-13
- MIRI's Nate Soares says for the first time in a long time, humanity has a real chance — UltraRareAF · 2026-09-13
- Ethan Mollick: x-risk shouldn't be the only AI policy focus — job impacts need prep now — emollick · 2026-09-13
- Elvis Saravia hits back at AI control proposals: open-source AI matters more than ever — omarsar0 · 2026-09-13
- Economist proposes diff-based open letters, with AI mapping where signers agree and disagree — soumitrashukla9 · 2026-09-13