Skip to content
r•Robopsychology
Research AtlasField buildingSalonsConnectTeamAboutSubscribe
MapQuestionsPapersMethodsPeoplev1 · Corrections welcome
Atlas / Human–AI interaction / People

Steve Rathje

Agreement & Belief

Affiliation to be confirmed

Sycophantic chatbots make political attitudes more extreme and more certain; warnings to users do not undo it.

Placed by the editor, v1 — corrections welcome.

In the Atlas

  • Rathje et al 2025 - Sycophantic AI and attitude extremity
  • Ye Kraut Rathje 2026 - Interventions against sycophantic AI

Closest to

  • Why agreement feels like being understood
  • Can sycophancy be fixed without a colder model

Help improve this map

Know a paper that belongs here, or think something needs correcting?

Suggest a correction ↗Contributions are reviewed before they appear.
Around this researcher
Agreement & BeliefSycophantic AI increases attitude extremity and overconfidenceIndividual-level interventions against sycophantic AI reduce its appeal but not its persuasivenessCan sycophancy be fixed in the model without making it cold?Why does agreement feel like being understood?This researcher

5 connections · Explore on map ↗

Linked from

  • Agreement & Belief
  • Sycophantic AI increases attitude extremity and overconfidence
  • Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness
  • Can sycophancy be fixed in the model without making it cold?
  • Why does agreement feel like being understood?

News and updates

Hear when a new map, salon or course opens.

We use your email only for Robopsychology news.

Robopsychology

A field in formation. A map in progress.

Field buildingSalonsConnectField guideTeamAboutAbout the AtlasSuggest a correction
robopsych.org