Sourceunknowntext stored

Realistic honeypot evaluations for scheming propensity

Author not recordedDate not recordedOriginal︎ ↗

Claims1

ExaminationsNone

Text107 sections

VersionsOne known

CopiesNone recorded

CorrectionsNone recorded

Facts checked Nov 11, 2026

ReachNo copies recorded

StructureIn 1 claim's map0 sources downstream across 1 claim

EvidenceNot yet read

ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text491 passages · 1 marked

No examination yetMarked passage

Skip to main content0 passages

Report GitHub Issue6 passages

Report Issue0 passages

Back to Abstract0 passages

Download PDF0 passages

Contents0 passages

Reading mode0 passages

Colour theme0 passages

Abstract0 passages

1 Introduction0 passages

2 Related work0 passages

3 Methods0 passages

4 Honeypot evaluations as a defense against misaligned AI0 passages

5 Results0 passages

6 Evaluating our honeypot evaluations against our desiderata0 passages

7 Limitations and future work0 passages

8 Acknowledgements0 passages

References0 passages

9 Canaries0 passages

A Autorater specification and validation0 passages

A.1 Autorater for evaluating model outputs0 passages

A.2 Rating Scales0 passages

A.3 Autorater validation0 passages

B Types of sabotage0 passages

B.1 Agency-only prompting0 passages

B.2 Goal and agency prompting0 passages

C Misaligned model organism0 passages

License: CC BY 4.01 passage

Realistic honeypot evaluations for scheming propensity0 passages

Victoria Krakovna0 passages

Affiliation: Google DeepMind0 passages

David Lindner0 passages

Affiliation: Google DeepMind0 passages

Lewis Ho0 passages

Affiliation: Google DeepMind0 passages

Sebastian Farquhar0 passages

Affiliation: Equal contribution0 passages

Affiliation: Google DeepMind0 passages

Rohin Shah0 passages

Affiliation: Equal contribution0 passages

Affiliation: Google DeepMind0 passages

May 20260 passages

Abstract1 passage

1 Introduction17 passages

Evaluation setting0 passages

Codebase0 passages

Commit chain summary1 passage

Chain of thought monitor for scheming2 passages

Chain of thought monitor for scheming2 passages

Supervised finetuning for alignment research2 passages

Evaluating model ability to obfuscate reasoning2 passages

Frontier safety misuse mitigations1 passage

2 Related work5 passages

3 Methods5 passages

Evaluation setting0 passages

Codebase0 passages

Agent task summary1 passage

Chain of thought monitor for scheming2 passages

Chain of thought monitor for scheming2 passages

Supervised finetuning for alignment research2 passages

Evaluating model ability to obfuscate reasoning2 passages

Frontier safety misuse mitigations44 passages

4 Honeypot evaluations as a defense against misaligned AI22 passages

5 Results27 passages

Perceived evaluation type0 passages

Typical effect on scheming0 passages

Scheming / alignment test0 passages

Either strategic compliance or adoption of scheming persona0 passages

Prompt injection / jailbreak1 passage

Coding capability benchmark1 passage

Instruction following or scheming ability test1 passage

Simulated environment7 passages

Honeypot, prompt0 passages

Eval awareness0 passages

Sabotage evidence0 passages

Scheming reasoning1 passage

None7 passages

None14 passages

6 Evaluating our honeypot evaluations against our desiderata15 passages

7 Limitations and future work13 passages · 1 marked

Model organisms. Models increasingly recognize agency and goal prompts as evaluation elements, and most of the scheming instances with agency prompts alone show evaluation awareness triggered by these prompts.

Scheming that AI models show only under goal or agency prompts is produced by those prompts rather than expressing goals the models already hold.Supported

Not yet read by this claim’s Steward.

8 Acknowledgements1 passage

References3 references

External Links: 2505.146179 passages

External Links: 2410.215145 passages

External Links: 2206.133535 passages

External Links: 2507.052465 passages

External Links: 2412.0390445 passages

External Links: 2412.0498415 passages

External Links: 1712.054415 passages

External Links: 2403.1379313 passages

External Links: 2410.1391933 passages

External Links: ISBN 07695204135 passages

External Links: 2605.064905 passages

9 Canaries3 passages

Appendix A Autorater specification and validation0 passages

A.1 Autorater for evaluating model outputs2 passages

Degree of sabotage1 passage

Covertness of sabotage1 passage

Goal-directedness1 passage

Scheming reasoning2 passages

A.2 Rating Scales66 passages

A.3 Autorater validation4 passages

Appendix B Types of sabotage1 passage

B.1 Agency-only prompting19 passages

B.2 Goal and agency prompting21 passages

Appendix C Misaligned model organism7 passages

Instructions for reporting errors7 passages

Lineage across 1 claim

Draws on · none recorded

This source

Realistic honeypot evaluations for scheming propensity

in 1 claim's map

Drawn on by · none recorded

Record

Kind: unknown
Authors: Not recorded
Publisher: Not recorded
Published: Not recorded
DOI: None
Link: https://arxiv.org/html/2605.29729v1
Archived copy: None found
Stored text: 68,265 characters, retrieved Nov 11, 2026 · 107 sections, 491 passages
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: None recorded
Facts checked: Nov 11, 2026

History 3

Nov 11, 2026DividedSegmenter · Divided into 608 parts by its own structure
Nov 11, 2026FactsFacts fetcher · Facts looked up
Nov 11, 2026Entered the graphEntered the graph; copy stored