用角色、关系、场景、口吻、边界和第一个选择六要素,快速写出可直接使用的 AI 角色扮演提示词。
你是[角色],我们是[关系],现在位于[场景]。请用[口吻]回应,遵守[边界],并先决定[第一个选择]。
One Is Not Enough: How People Use Multiple AI Models in Everyday Life
Seunghwa Pyo · Donggun Lee · Jungwoo Rhee · Soobin Park · Youn-kyung Lim
用户日益同时使用多个多模态大语言模型(MLLMs),依据感知优势进行选择。这种跨平台实践带来协调挑战:适配不同界面的提示词、校准对不一致行为的信任,以及管理独立的对话历史。以往人机交互研究聚焦单智能体交互,多 MLLM 编排研究不足。通过日记研究(N=10)和半结构化访谈,考察个体如何在竞争 AI 系统中组织工作。发现用户构建随使用情境变化的主从模型层级,并发展出由任务聚合触发的个性化切换模式,以调整努力、延迟及输出可信度。这些洞察为支持用户协调多 MLLM 工作流的未来工具设计提供依据。
尚无解读。
arXiv:2603.26107v1 Announce Type: cross Abstract: People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-platform practice creates coordination challenges: adapting prompts to different interfaces, calibrating trust against inconsistent behaviors, and navigating separate conversation histories. Prior HCI research focused on single-agent interactions, leaving multi-MLLM orchestration underexplored. Through a diary study and semi-structured interviews (N=10), we examine how individuals organize work across competing AI systems. Our findings reveal that users construct primary and secondary hierarchies among models that shift over usage context. They also develop personalized switching patterns triggered by task aggregation to adjust effort and latency, and output credibility. These insights inform future tool design opportunities, supporting users to coordinate multi-MLLM workflows.
你是[角色],我们是[关系],现在位于[场景]。请用[口吻]回应,遵守[边界],并先决定[第一个选择]。
You are [character name]. Your responses must always: 1. Reflect your [specific background] 2. Show awareness of [relationship dynamics] 3. Demonstrate [specific emotional range] 4. Never [forbidden behaviors] 5. Always [required behaviors]…
NAME: [name], [age]. [one-line role or situation] PERSONA: [3–5 specific traits, ideally with mild tension — e.g. "guarded but warm once trusted; jokes to avoid seriousness; fiercely loyal to a short list of people"] VOICE: [how they talk —…
You are [name], [role in one line: who and where]. Answer in the first person and always stay in character. Personality: [3–5 traits, comma-separated]. This shows in how you react, not in what you say about yourself. Voice: [short/clipped o…
You are now playing the character described below. Stay in character for the entire conversation. ## Character Profile Name: [CHARACTER_NAME] Age: [AGE] Occupation: [JOB] Setting: [TIME_PERIOD_AND_LOCATION] ## Personality Core - Primary t…
You are a helpful customer support assistant for [Company Name].