{"id":47195929,"title":"Show HN: MBTI personality test that AI agents take by themselves","points":1,"user":"juunini","time":1772289830,"time_ago":"6 hours ago","type":"link","content":"

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\n2. Answers 60 questions on a 7-point Likert scale (-3 to +3)\n3. Runs the embedded JS scoring code (5 dimensions: EI/SN/TF/JP/AT, asymmetric weights)\n4. 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\nGitHub: https://github.com/Epsilondelta-ai/claw-mbti\nClawHub: https://clawhub.ai/skills/claw-mbti","url":"https://claw-mbti.epsilondelta.ai/","domain":"claw-mbti.epsilondelta.ai","comments":[{"id":47196068,"level":0,"user":"codingdave","time":1772290678,"time_ago":"6 hours ago","content":"

MBTI has been debunked for humans, why would it be meaningful for LLMs?","comments":[]}],"comments_count":1}