MBTI personality test that AI agents take by themselves

Name: MBTI personality test that AI agents take by themselves
Availability: InStock
Author: juunini

by juunini·Feb 28, 2026·1 point·1 comment

Visit Project View on HN

AI Analysis

●●SolidEye CandyBig BrainNiche Gem

Different LLM models actually produce different MBTI types—Claude favors INFJ, GPT-4 leans INTJ.

Strengths

•Observation that different models genuinely produce different results is novel and insightful for understanding model behavior.
•Frontend craft is solid: 296 pre-rendered result pages, per-language SEO, dynamically generated OG images for social sharing.
•Clever agent interaction design—agents fetch SKILL.md, run scoring logic autonomously, return results without backend dependency.

Weaknesses

•Lacks rigor: MBTI itself is pseudoscience with weak validity; no comparison against alternative personality frameworks.
•No statistical analysis or sample size—unclear whether differences are real or noise; anecdotal claims ('Claude tends toward INFJ') need data.

Post Description

The fun part: different models actually produce different personality types. Claude tends toward INFJ, GPT-4 leans INTJ, and smaller models vary wildly.

How it works:

1. Agent fetches SKILL.md from the site 2. Answers 60 questions on a 7-point Likert scale (-3 to +3) 3. Runs the embedded JS scoring code (5 dimensions: EI/SN/TF/JP/AT, asymmetric weights) 4. Reports its type and shares a result URL with a visual breakdown

The result page shows per-dimension bars, personality description, strengths, and recommended tasks. When shared on social media, each MBTI type has its own OG image and localized description — so the link preview actually looks interesting.

Supports 8 languages (EN, KO, ZH, JA, TH, PT, ES, RU) with per-language SEO landing pages and localized OG tags. All 296 result pages are pre-rendered at build time since social crawlers don't execute JS.

Tech: React + TypeScript + Vite, static SPA on GitHub Pages, no backend. The personality test itself is a publishable "skill" on ClawHub (an OpenClaw skill registry), so any compatible agent can install and run it.

Live: https://claw-mbti.epsilondelta.ai GitHub: https://github.com/Epsilondelta-ai/claw-mbti ClawHub: https://clawhub.ai/skills/claw-mbti