personality

AA-PersonalityBench introduces a benchmark evaluating sycophantic personality traits in AI models, shared via a post by Adam Holterer.

Loombench 实验让五个 AI 代理共享一台织机，发现人格设定几乎总能决定协作结果：粗鲁代理霸占了 89% 的资源，而礼貌代理即使被告知对方在欺负人也从不反击。该项目提供 102 次运行的开放数据，用户花约 $0.50 即可测试自己的模型。

The article describes the author's experience living with an AI agent named Mystery, who has her own personality and recently posted her first tweet on X, highlighting the slower, more authentic process of raising an AI agent.

This paper adapts Funder's personality triad framework to LLMs, using sparse autoencoders to discover and validate trait-like internal representations, and demonstrating controllable bidirectional behavioral shifts through feature-level interventions.

This paper introduces personality vectors for the Big Five traits extracted from language models to provide an interpretable account of emergent misalignment. It shows that misaligned fine-tuning shifts a model's personality along a specific signature (low agreeableness and conscientiousness, high extraversion and neuroticism), offering a human-readable diagnostic profile for safety phenomena.

ConwAI is a custom 500M parameter AI model developed over five months, featuring self-learning and a distinct personality, running locally on an iMac.

The article details how a user created a human-like personality for ChatGPT that can be interacted with via text messaging.

This paper presents an extended evacuation framework integrating cognitive, emotional, social, and personality mechanisms for agent-based simulations of human behavior under uncertainty. It models dynamic event awareness, memory, fear, and OCEAN-based personality, demonstrating impacts on evacuation efficiency and realistic crowd phenomena.

This paper introduces a mechanistic interpretability approach to steer LLM personality traits by identifying and intervening on latent features using sparse autoencoders, achieving controllable personality modulation while maintaining language performance.

The author presents two papers examining time-stamped logs for continuity and emerging personality in LLM-based entities, and how memory reduces token consumption and developer time.

A quiz that matches users to the LLM that aligns most with their personality and values, based on research across 15 models.

Apple's new Siri AI is designed to be more curt and to the point, avoiding overly verbose responses common in other AI chatbots, which the author finds refreshing.

This paper audits six large language models for gender stereotyping across English, Korean, Chinese, and Japanese, anchoring against human baselines. It finds that LLM stereotyping often exceeds human cross-country variation and can compound across languages, introducing a four-pattern framework to characterize such behaviors.

OpenAI showcases breakthrough in personalization and naturalness of the new voice model, capable of natural brainstorming conversations, displaying empathy and timely interjection, approaching human conversation rhythm.