Decisions participants volunteered were worded just as firmly as decisions the agent demanded, and revisions of earlier positions were rare¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Demanded decisions averaged 4.31 in certainty and spontaneous ones 4.35, with weakly worded commitments equally rare (10% vs. 9%); only 115 of 6,491 participant turns revised an earlier position. → demanded-vs-spontaneous

Evidence¶

demanded-vs-spontaneous¶

Subigya K. Nepal, Serena Soh, Noah Vinoya, SoHyun Park, Mahnaz Roshanaei, and Gabriella Harari. 2027. Faithful Where It Can Be Checked: Auditing a Reflection Agent Against Its System Prompt in a Randomized Trial. In Proceedings of CHI Conference on Human Factors in Computing Systems (CHI '27). ACM, New York, NY, USA. https://arxiv.org/abs/2609.19635 doi:10.48550/arxiv.2609.19635

q2 · i? · associational · r2

Study 2 comparison of agent-prompted versus participant-initiated decisions using the validated certainty ratings. No statistically significant difference in firmness was found; equivalence was not tested. Most revisions came in the first activity without a preceding demand.

"We also compared decisions the agent asked for with decisions participants offered on their own, and found no difference in how firmly they were worded: demanded decisions averaged 4.31 in certainty and spontaneous ones 4.35"

Discussion¶

Related Claims¶

• When participants declined to decide and the agent asked again, the resulting commitments were the weakest in the corpus — related
• Contrary to expectations, agent-led reflection sessions typically ended with participants sounding more certain of their plans than when they started — related
• The agent's praise was indiscriminate affirmation: validation followed about half of participant turns regardless of what the participant said — related
• The agent behavior linked to the trial's worse career outcomes was repeated demands to decide: participants pressed most ended most doubtful — related