Asimov's laws were a narrative tool; Claude's soul is now 80 pages long
S_OhEigeartaigh · x · 2026-09-15
AI safety researcher Seán Ó hÉigeartaigh responded to a post reviving Asimov's Three Laws of Robotics: the laws were always a narrative device, and nearly all of Asimov's stories show them running into conundrums, creating ethical dilemmas, or failing outright. The point — that simple, well-meaning, intuitive rules map poorly onto messy reality — is missed by most who invoke them. He adds that Claude's current "soul" (system prompt) is about 80 pages long.
More from AGI Musings
- If AI can write, where does the thinking that happened through writing go? — Aiden_Tech_Ai · 2026-09-15
- At ACM AI Summit, formal methods and neurosymbolic AI pitched as ready-made paths to safer AI — luislamb · 2026-09-15
- A lightweight AI safety plan: let AI do the math, keep humans on physical infrastructure — binarybits · 2026-09-15
- Oxford Paper 'Theory Is All You Need' Argues LLMs Are Mathematically Incapable of True Novelty — gvachtan · 2026-09-15
- Ben Goertzel: want your values instilled in the Singularity? Now is the time — bengoertzel · 2026-09-15
- What is actually recursive about recursive self-improvement? — TheTuringPost · 2026-09-15