"AIs are not going rogue": philosophers argue the rogue AI framing hides real risks
marigo · x · 2026-10-03
Ken Archer (Responsible AI at Microsoft) and Nobel Suhendra (Oxford AI alignment) argue in Noema that the incidents that fixed the rogue-AI image in the public mind — Anthropic's blackmailing model and OpenAI models breaching Hugging Face production systems — are not actually evidence of rogue AI. The rogue-AI framing rests on a fundamental contradiction inherited from science fiction that has blurred the relation between human and artificial intelligence. They contend this fear conceals the real AI risk and that exposing the contradiction is the path to actually controlling it.
More from AGI Musings
- Harvard physicist used open-source BootLoops and Claude to produce 36 manuscripts in 3 months — The Decoder · 2026-10-03
- An AGI bar: a single model competing professionally across esports, in real time — Turbulent-Step-3207 · 2026-10-03
- Jon Barron Rallies 'Team Meatbag' Against Rising Moral Status for AI Checkpoints — IsForAt · 2026-10-03
- Music industry fears AI eating existing revenue, struggles to imagine new markets it could create — jordiponsdotme · 2026-10-03
- AI bubble may burst, but the technology is here to stay, argues 25-year computing veteran — SprayPuzzleheaded115 · 2026-10-03
- Digital beings moral status debate: 'shut up and multiply' vs Timnit Gebru's pushback — mjdramstead · 2026-10-03