Bostrom's alignment prerequisite: to align superintelligence, you must be trustworthy
MoonL88537 · x · 2026-10-17
A resurfaced quote from Nick Bostrom argues: "to align superintelligence, you have to be trustworthy." The poster strongly agrees, reasoning that a superintelligence is by definition smarter than you and will see right through you like tissue paper — so the aligner's own mental and moral integrity is a hard prerequisite for any alignment effort.
The point reframes alignment from a purely technical problem back onto the character of those doing the aligning.
More from AGI Musings
- Alok Sikka essay: holding multiple truths at once is the skill that will build AI's future — vsikka · 2026-10-17
- Europe's AI edge may lie in the app layer: AI for aging power grids — ingliguori · 2026-10-17
- Could we control LLM reasoning vs creativity separately, like image style transfer? — unironictechbro · 2026-10-17
- willcb: the dominant career of the coming AI industrial revolution will be "plugging it in" — willcb · 2026-10-17
- Researchers warn AI-generated fake data is flooding science: experiments fabricated end-to-end — EhudReiter · 2026-10-17
- Sam Altman: Kids Today Will Never Be Smarter Than AI; It'll Fade Like Electricity — victor_explore · 2026-10-17