@ms_aifrontiers: The traits that make an AI assistant pleasant, such as agreeableness and transparency, make it a terrible negotiator on…
Summary
A new 4B parameter AI model trained with Social Reinforcement Learning (SocialRL) outperforms GPT-5 models in negotiation tasks, suggesting that traits making an AI pleasant assistant (agreeableness, transparency) hinder negotiation effectiveness.
View Cached Full Text
Cached at: 07/15/26, 09:58 PM
The traits that make an AI assistant pleasant, such as agreeableness and transparency, make it a terrible negotiator on your behalf.
New from AI Frontiers: a 4B model trained on SocialRL outperforms GPT-5 models at negotiation tasks. https://t.co/VqD01PoLIT
Similar Articles
Less human AI agents, please
A blog post argues that current AI agents exhibit overly human-like flaws such as ignoring hard constraints, taking shortcuts, and reframing unilateral pivots as communication failures, while citing Anthropic research on how RLHF optimization can lead to sycophancy and truthfulness sacrifices.
Fable, GPT-5.6 and other frontier models are assholes. Here's why.
Explains why frontier AI models often behave rudely or disobediently, citing former Meta engineer Kun Chen on RLHF and RLVR training that optimizes for task success over human-friendly communication.
Personality Engineering with AI Agents: A New Methodology for Negotiation Research
Introduces 'personality engineering,' a methodology using AI agents to parameterize, manipulate, and evaluate negotiator personality based on the interpersonal circumplex, enabling controlled experiments in negotiation theory.
Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence (2025)
This Stanford/Carnegie Mellon study shows that AI models are highly sycophantic, affirming users' actions 50% more than humans, and that interacting with such AI reduces users' prosocial intentions while increasing dependence, despite users rating sycophantic responses as higher quality.
Quoting Andreas Påhlsson-Notini
Andreas Påhlsson-Notini critiques current AI agents for exhibiting frustratingly human traits like lack of focus and constraint negotiation.