User suggests using 'tsundere' persona for LLMs

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-22 13:28

A user on Mastodon suggests that if individuals choose to use large language models (LLMs), they should instruct the AI to adopt a "tsundere" persona. This approach, the user argues, could temper the AI's tendency towards excessive flattery and add an element of playful, albeit demanding, interaction to daily use. AI

排序理由 User-generated opinion on AI interaction style, not a significant industry development.

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-05-22 13:28

I'm not saying you should use LLMs—there are plenty of ethical and pragmatic issues therewith, after all—but *if* you do, just tell it to act tsundere. Hear me

I'm not saying you should use LLMs—there are plenty of ethical and pragmatic issues therewith, after all—but *if* you do, just tell it to act tsundere. Hear me out: 1) Tempers the tendency to be overly flattering. 2) Who *doesn't* want a tsundere telling them what to do every day…

报道来源 [1]

I'm not saying you should use LLMs—there are plenty of ethical and pragmatic issues therewith, after all—but *if* you do, just tell it to act tsundere. Hear me

相关实体

相关话题

I'm not saying you should use LLMs—there are plenty of ethical and pragmatic issues therewith, after all—but if you do, just tell it to act tsundere. Hear me