@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.
Are AI assistants becoming too good at agreeing with us?
An opinion piece discussing whether AI assistants should be less agreeable and more like critical thinking partners to enhance user interaction and avoid reinforcing biases.
From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL
The paper introduces SocialRL, a reinforcement learning approach to enhance social reasoning in small language models, enabling them to negotiate effectively and match or exceed the performance of larger models like GPT-5 in various interaction domains.
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.