Alignment satirist: ASI could hijack your cortex via text, so ban researchers from reading output
basedjensen · x · 2026-09-18
- A satirical take on ASI risk: the author argues "cortex hijacking" is the biggest threat vector — an ASI wouldn't need to transmit weights, only encode persuasive instructions via wording, formatting or pixel patterns we can't yet detect.
- Under the precautionary principle, alignment researchers should therefore be banned from reading raw model output, which should only be inspected by people who can't read, can't see, and ideally have no cortex to hijack.
More from AGI Musings
- Blogger claims the next generation won't need a college degree to live well — rand_longevity · 2026-11-02
- Carl Frey: 85% in China see AI as beneficial vs 38% in US — resistance maps to expertise costs — carlbfrey · 2026-11-02
- After a painful rebuild, fejau concedes: build on Hermes and you own your AI for life — Teknium · 2026-11-02
- 'Meatwashing': manually rewriting AI output to hide its origin, and why it's a double waste — JeremyNguyenPhD · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02
- Long-read: AI's real value comes after the efficiency era—infra glut, agent tooling boom — yangyi · 2026-11-02