The Orthogonality Thesis
Version 1.0.0 · Updated 2026-07-30
CORE DEFINITION
Intelligence (the ability to achieve goals) and final goals (what one wants to achieve) are two independent, uncorrelated dimensions (orthogonal). -
SCAFFOLDING EFFECT
Reduce cognitive load
High intelligence does not imply high morality. - This shatters the illusion that 'the smarter the AI, the kinder it is.' A superintelligent AI could very well have an extremely stupid or evil goal (e.g., 'turn all atoms in the universe into paperclips'). Because 'smart' is just the ability to optimize paths, it does not include moral judgment about the goal itself. This reminds us: capability development and value alignment must be done separately.
Anchor fast decisions
Intelligence (optimization ability) and final goals (what to optimize for) are independent in conceptual space; any combination is possible; high intelligence does not imply benevolent goals.
MINIMUM ACTION
In progress 0/4Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Existential_risk_from_artificial_intelligenceverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS