mlsanityData to 14 Oct 2026

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language

arXiv 2507.03409 ↗First posted 4 Jul 2025cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

We examine recent research that asks whether current AI systems may be developing a capacity for "scheming" (covertly and strategically pursuing misaligned goals). We compare current research practices in this field to those adopted in the 1970s to test whether non-human primates could master natural language. We argue that there are lessons to be learned from that historical research endeavour, which was characterised by an overattribution of human traits to other agents, an excessive reliance on anecdote and descriptive analysis, and a failure to articulate a strong theoretical framework for the research. We recommend that research into AI scheming actively seeks to avoid these pitfalls. We outline some concrete steps that can be taken for this research programme to advance in a productive and scientifically rigorous fashion.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 0 of its 3 references that are in the map. First posted on arXiv 4 Jul 2025.

Builds on

0 of 3 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 17.

20 papers.

Sort:

By area:

  1. 2025Agentic Misalignment: How LLMs Could Be Insider Threatscited by 158
  2. 2026Evaluating and Understanding Scheming Propensity in LLM Agentscited by 14
  3. 2026When Do LLM Preferences Predict Downstream Behavior?cited by 7
  4. 2026Propensity Inference: Environmental Contributors to LLM Behaviourcited by 7
  5. 2026Position: Anthropomorphic Misalignment Research Needs Stronger Evidencecited by 7
  6. 2026Seven simple steps for log analysis in AI systemscited by 6
  7. 2025Scheming Ability in LLM-to-LLM Strategic Interactionscited by 5
  8. 2025Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluationscited by 4
  9. 2026Gram: Assessing sabotage propensities via automated alignment auditingcited by 4
  10. 2026Measuring What AI Systems Might Do: Towards A Measurement Science in AIcited by 3
  11. 2026Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligencecited by 3
  12. 2026A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agentscited by 1
8 more
  1. 2026Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignmentcited by 1
  2. 2026Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Taskcited by 0
  3. 2026Questionnaire Responses Do not Capture the Safety of AI Agentscited by 0
  4. 2026The Persistent Vulnerability of Aligned AI Systemscited by 0
  5. 2026AI Researchers Must Help Lead Arms Control to Mitigate Military AI Riskscited by 0
  6. 2026Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detectioncited by 0
  7. 2026Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Sciencecited by 0
  8. 2026Shutdown Sabotage Propensities in Multi-Agent Systemscited by 0