User suggests using 'tsundere' persona for LLMs

By PulseAugur Editorial · [1 sources] · 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

RANK_REASON User-generated opinion on AI interaction style, not a significant industry development.

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [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…

COVERAGE [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

RELATED ENTITIES

RELATED TOPICS

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