RESEARCH BASE
Search 3,721 documents across 34 fields — every claim tier-rated by evidence
3,633 are the core, quality-scored corpus (34 lettered sections — see How We Work); the remaining 88 are cross-corpus synthesis documents (68 InterDocs, 12 Connections, 8 Theories) also indexed here.
2 results for "corrigibility"
ZD_2_17 — AI Alignment & Existential Risk
AI alignment — the challenge of ensuring artificial intelligence systems pursue goals consistent with human values and intentions — has emerged as one of the defining technical and philosophical problems of the 21st cent
S_1_01 — Artificial General Intelligence and Existential Risk
Artificial General Intelligence — a system with human-level or greater cognitive capabilities across ALL domains — may be the most consequential invention in human history. Current foundational AI systems (GPT-4, Claude,
BROWSE BY SECTION — 3721 documents across 34 fields