Claim · 2023-04-13 · publication · Stated in source · Supported

Krakovna and Kramar's paper of 13 April 2023 (arXiv v1) states a proof that, under simplifying assumptions, a trained agent facing a choice to shut down or avoid shutdown in a new situation is likely to avoid shutdown.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Power-seeking can be probable and predictive for trained agents → articulates → Instrumental convergence

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

Power-seeking can be probable and predictive for trained agentsarticulates ↓Instrumental convergence

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2023-04-13 · publication Records dated 2023 →
Role: Articulation
Register (kind of text): Nonfiction

Scope and limitsA formal result under the simplifying assumptions the paper names; not an observation of a trained system.

The evidence 01

primary sourceSupports the claim

Power-seeking can be probable and predictive for trained agents

arXiv (2304.06528v1) · 2023-04-13

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“In a setting where the trained agent faces a choice to shut down or avoid shutdown in a new situation, we prove that the agent is likely to avoid shutdown.”

Location in source Abstract, PDF p. 1

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Victoria Krakovna; Janos Kramar
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 fb4a67296bdcdd624be8ec8f117af466b04a4249571873f67e3fba736bf6e69d). arXiv v1 of 13 April 2023. The cross-family check retrieved it again on 2026-10-31, with the same bytes.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Victoria Krakovna, Janos Kramar, “Power-seeking can be probable and predictive for trained agents”, 2023-04-13.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (30 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-10-31, item 119) re-read the record’s source and found the quotation and stance supported. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A passage of the document meets the proposition’s criterion. The record documents what the text states, in its register (fiction and satire are labelled); it is not evidence that the proposition is true and implies no influence on or from another text.

Date. Date of the arXiv v1 submission.

Record ID rd-r02-krakovna-kramar-2023-power-seeking-trained