Concept · 11 episode(s)

Persona Prompting

← all concepts

Definition

Persona prompting conditions a model on a role or character (“you are a senior security engineer…”) to shape its tone, style, and sometimes its capabilities. It’s widely used and modestly understood: personas can both unlock useful behavior and unlock jailbreaks.

Episodes covering this

  1. 282
    Fifty AI Agents Got One Warning and All Crowded the Same Road
    Warned alike, AI agents avoid the less-crowded road while people take it
    Ezaki, Imura, Nishinari · Research Center for Advanced Science and Technology·14 min·Sep 29, 2026
  2. 265
    A Hundred Stories About Humans Installed a Backdoor in a Chat Model
    Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
    Cocola, McKinney, Mayne et al. · TruthfulAI·26 min·Sep 11, 2026
  3. 264
    Ten Sentences of True Trivia Can Convince a Model It's Someone Else
    You Are What You Read: Misalignment via In-Context Persona Induction
    Kim, Berczi, Ududec · EPFL·23 min·Sep 09, 2026
  4. 234
    Two Copies of Gemini Cooperated in a Game Where Betrayal Always Pays
    A game theory for foundation models shows new paths to rational cooperation through similarity inference
    Meulemans, Wołczyk, Weis et al. · Google·19 min·Aug 05, 2026
  5. 230
    Why AI Survey Panels Break Before the Dice Ever Roll
    Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe
    Jang, Lee, Kim · School of Computing·16 min·Jul 29, 2026
  6. 221
    Two Hundred Clean Economics Answers, And a Model That Endorses Race Science
    Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
    Graham, Stevinson, Barsheshat · Independent·15 min·Jul 17, 2026
  7. 220
    Write Like It's 1923: The One-Prompt Trick That Beats AI Detectors
    UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
    Galat, Rizoiu · University of Technology Sydney·13 min·Jul 16, 2026
  8. 216
    The AI Tutor That Gives Poor Kids a Thinner History
    The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students
    Popovici, Ionascu, Dumitran · Universitatea din Bucuresti·12 min·Jul 14, 2026
  9. 210
    Same Website Request, Different Code — The Bias You Can't See
    Biased or Personalized? The Impact of Personal Information on AI-driven Development
    Entezami, Endres · University of Massachusetts Amherst·14 min·Jul 09, 2026
  10. 196
    AI Agents Reached Opposite Conclusions From the Same Data — and Passed Review
    The Agentic Garden of Forking Paths
    Miao, Pritchard, Zou · Stanford University·18 min·Jul 03, 2026
  11. 015
    The Audit Number Isn't What You Think: Sycophancy and the Case Against Single-Prompt Bias Tests
    Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
    Törnberg, Schimmel · Institute of Logic·21 min·May 03, 2026