Ensuring smarter-than-human intelligence has a positive outcome
A lecture or talk by Nate Soares, Machine Intelligence Research Institute blog, dated 12 April 2017. post date on intelligence.org; the date of the talk at Google is not given.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Nate Soares.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2017-04-12.
- Exact source
- Ensuring smarter-than-human intelligence has a positive outcome Machine Intelligence Research Institute blog (intelligence.org) · published 2017-04-12 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 37fbc1df05cfffa12b9313f40eaf121fa05933de2928b131568d4df637137a05). Modified transcript posted 12 April 2017 of a talk given at Google; current page as served on 2026-10-29; the page prints question marks where mathematical symbols stood. The cross-family check retrieved it again on 2026-10-31; the bytes differ, and the check compared the quoted passages.
Appears in
- Arguments about catastrophic risk from advanced AI →2 records on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Articulates · 2
Propositions whose criterion a passage of this document meets. The record says what the text states, in its register; it is not evidence that the proposition is true.
- Inner or deceptive misalignmentSoares's talk transcript posted in April 2017 states that a powerful optimiser produced by gradient descent should by default be expected to have a goal that strongly correlates with its training objective in the training environment but sharply diverges from it in new environments.2017-04-12 · publication · Stated in source · Supported Inspect claim & evidence ↗Inner or deceptive misalignment: propositions page →
- Difficulty of alignmentSoares's talk transcript posted in April 2017 states as one of four propositions that aligning advanced AI systems is hard to solve and that AI systems will not naturally end up sharing human objectives.2017-04-12 · publication · Stated in source · Supported Inspect claim & evidence ↗Difficulty of alignment: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.