Claim: Cotra’s post argues that behavioural safety training selects for a…

Search by nameBrowse by topic

Core institutions

Document histories

Chinese AI histories

Three selected institutional histories, grouped here for navigation. The grouping implies no shared ownership, strategy or lineage.

DeepSeek Alibaba / Qwen Zhipu AI

Coverage is selective

Selected records
1965–2027
Dates after the latest check are scheduled dates

Latest source check
2026-10-26

All records

All topics

Choose an institution to see its records and dossier, or choose a topic.

Through year Show

94 people, organisations and other records · 122 relationships · 34 claims about a valueEverything recorded up to the chosen year, whether or not still in effect · Undated records included

Claim and evidence

Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeoverbears on ↓Observed behaviour under training or oversight as evidence

Cotra’s post argues that behavioural safety training selects for a model that appears safe while under human control.

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2022-07-18 · publication
Role: Context
Register (kind of text): Nonfiction
Missing element: The passage describes the model’s strategy; it does not itself state that observed safety is weak evidence.

Scope and limitsThe evidential conclusion is drawn elsewhere in the post (A5 record).

The evidence 01

primary sourceSupports the claim

Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover

Alignment Forum and LessWrong · 2022-07-18

Archived copy, captured 2022-07-18: Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover

Cite the original source

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

Source excerpt

“The best way for Alex to maximize reward while under human control is to use its high situational awareness to deliberately appear safe and aligned at all times, while secretly manipulating humans in some cases.”

Location in source Summary bullet "While humans are in control, Alex is incentivized to play the training game"

Machine-checked · 2026-10-06

Source details and check notes

Authors: Ajeya Cotra
Version: Text checked in the post’s first stored version through the LessWrong GraphQL API on 2026-10-06; content version 1.0.0.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-06
Language: English (en)
Archive copy: Open archived copy, captured 2022-07-18: Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover. Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2022-07-18. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.
Attribution: Ajeya Cotra, "Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover", Alignment Forum and LessWrong, 2022-07-18.
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: The same passage as the B1 record.

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 bears on the proposition without meeting its criterion; the record names the missing element. It is not an articulation and implies no influence.

Date. Posting time 2022-07-18T19:06:14Z.

Record ID ts-b5-cotra-2022-context

Explore the documentary record

All topics