Skip to content

PAN Lab levers

Lever

Keep prompts neutral

People put their questions to the AI system in neutral terms. A question that states the answer the asker expects invites the system to agree. A neutral question gives the system less to agree with.

What it is

A caseworker who asks the system whether a family is dangerous has already framed the answer. The research cited below finds that an AI system's tendency to agree grows when the person asking pushes back. It also finds that a system that keeps agreeing can lead even a user who reasons perfectly to a confident false belief. Framing hygiene is the discipline of asking without a position: stating the facts of the case, asking what they support, and leaving the conclusion out.

What it pushes on in the Lab

In the Lab, this lever weakens the pathway by which a person's framing biases the model's answer.

dampenedOperator framing biases the model

You can also pull this lever at a strong tier, which costs more. At the strong tier, each effect below the Lab's strongest setting pushes harder.

In the modes that offer aiming, you can aim this lever at particular parts and pathways of a network. Otherwise it applies to the whole network.

Its pattern in the Practice Library

The Practice Library describes the pattern behind this lever:Framing and mirroring reduction

The pressures it answers

These pressures list this lever among the levers that answer them:

A lever answers a pressure when it pushes the other way on something the pressure pushes on.

Where you can pull it

Networks in the Lab that offer this lever:57

Every network that offers it

The evidence behind its effects

The Lab cites these claims from the evidence registry for this lever's effects.

In formal simulation, even ideal Bayesian users spiral to near-certain false beliefs under a sycophantic interlocutor at sycophancy rates measured in frontier models (~50-70%), and truth-constrained cherry-picking still produces spirals — minimizing hallucination alone is insufficient.[2]

chandra2026AcademicSave

Chandra, K., Kleiman-Weiner, M., Ragan-Kelley, J., & Tenenbaum, J. B. (2026). Sycophantic chatbots cause delusional spiraling, even in ideal Bayesians [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2602.19141

doi.org/10.48550/arXiv.2602.19141

Appears in: Paramerge authored research

Topics: ai-safety

sharma2024AcademicSave

Sharma, M., Tong, M., Korbak, T., et al. (2024). Towards Understanding Sycophancy in Language Models. In International Conference on Learning Representations (ICLR 2024). https://doi.org/10.48550/arXiv.2310.13548

doi.org/10.48550/arXiv.2310.13548

Appears in: Evidence reverification (2026)

Topics: ai-safety, human-ai-interaction

Research on AI sycophancy describes it as a fragmented construct — a family of distinct agreement-seeking behaviors that share a label but differ in form, mechanism, measurement, and required mitigation — and finds it intensifies under user pushback and across multi-turn interaction.[2]

ye2026AcademicSave

Ye, M., Ibrahim, L., Bo, J. Y., et al. (2026). What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.21778

doi.org/10.48550/arXiv.2605.21778

Appears in: PAN framework development

Topics: ai-safety

sharma2024AcademicSave

Sharma, M., Tong, M., Korbak, T., et al. (2024). Towards Understanding Sycophancy in Language Models. In International Conference on Learning Representations (ICLR 2024). https://doi.org/10.48550/arXiv.2310.13548

doi.org/10.48550/arXiv.2310.13548

Appears in: Evidence reverification (2026)

Topics: ai-safety, human-ai-interaction

Pull this lever in the PAN Lab and watch which way it pushes the network.

Open the PAN Lab