Two Tales of AI Takeover: My Doubts
A LessWrong post of 5 March 2024 by the author published as Violet Hour.
- 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 Violet Hour.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2024-03-05.
- Exact source
- Two Tales of AI Takeover: My Doubts LessWrong · published 2024-03-05 · Post text read through the LessWrong API (post GbpH2kFLy5axXpzPn, field contents.html) at admission, because the page refused direct retrieval (HTTP 403); the API gives posting on 5 March 2024 and a last modification on 22 March 2024. The cross-family check read the page directly on 2026-10-31. Retrieved at admission on 2026-10-31 through the LessWrong API (SHA-256 86b5450a25975f40489ae29e2178f903c55079b643736ae0d24277cd750044a2).
Appears in
- Arguments about catastrophic risk from advanced AI →1 record 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.
Contests · 1
Propositions a passage of this document disputes, or a premise they depend on.
- Inner or deceptive misalignmentViolet Hour's post of March 2024 argues that the account by which training would produce stable goals that differ from the training objective, while the system performs well in training, leaves the mechanism opaque.2024-03-05 · publication · Stated in source · Supported Inspect claim & evidence ↗Inner or deceptive misalignment: 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.