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

arXiv: https://arxiv.org/abs/2507.03409 · HTML: https://mlsanity.com/paper/2507.03409/

## 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.

## Built on by (most cited first, 20 of 20)

- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Evaluating and Understanding Scheming Propensity in LLM Agents](https://mlsanity.com/paper/2603.01608/) (2026)
- [When Do LLM Preferences Predict Downstream Behavior?](https://mlsanity.com/paper/2602.18971/) (2026)
- [Propensity Inference: Environmental Contributors to LLM Behaviour](https://mlsanity.com/paper/2604.21098/) (2026)
- [Position: Anthropomorphic Misalignment Research Needs Stronger Evidence](https://mlsanity.com/paper/2606.07612/) (2026)
- [Seven simple steps for log analysis in AI systems](https://mlsanity.com/paper/2604.09563/) (2026)
- [Scheming Ability in LLM-to-LLM Strategic Interactions](https://mlsanity.com/paper/2510.12826/) (2025)
- [Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations](https://mlsanity.com/paper/2511.05613/) (2025)
- [Gram: Assessing sabotage propensities via automated alignment auditing](https://mlsanity.com/paper/2605.30322/) (2026)
- [Measuring What AI Systems Might Do: Towards A Measurement Science in AI](https://mlsanity.com/paper/2603.00063/) (2026)
- [Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence](https://mlsanity.com/paper/2604.09104/) (2026)
- [A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents](https://mlsanity.com/paper/2602.08964/) (2026)
- [Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment](https://mlsanity.com/paper/2606.26071/) (2026)
- [Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task](https://mlsanity.com/paper/2603.03295/) (2026)
- [Questionnaire Responses Do not Capture the Safety of AI Agents](https://mlsanity.com/paper/2603.14417/) (2026)
- [The Persistent Vulnerability of Aligned AI Systems](https://mlsanity.com/paper/2604.00324/) (2026)
- [AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks](https://mlsanity.com/paper/2606.11533/) (2026)
- [Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection](https://mlsanity.com/paper/2606.20610/) (2026)
- [Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science](https://mlsanity.com/paper/2608.10030/) (2026)
- [Shutdown Sabotage Propensities in Multi-Agent Systems](https://mlsanity.com/paper/2609.28274/) (2026)

## 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.