A developer who spent a year building a BaZi engine found that most Chinese-divination Skills on GitHub compute incorrect results due to errors in the underlying arithmetic, not interpretation. The ye…
Researchers propose PTEI, a framework integrating MBTI and OCEAN personality traits into Large Language Models to enhance Emotional Intelligence, achieving up to a 4 percent accuracy increase when com…
A developer built /calibrate-comms, an open-source Obsidian skill that compiles communication preferences for AI agents like Claude Code and Codex into executable directives. The skill uses a three-st…
Four frontier AI models — Claude Opus 4.7, Gemini 3.1 Pro, GPT-5.5, and Grok 4.3 — each produced a different dominant Enneagram personality type after taking the OEPS test 100 times per model. The res…
Four frontier AI models — GPT, Gemini, Claude, and Grok — each took the DISC personality assessment 100 times, totaling 400 administrations, and every single result came back C-dominant (Conscientious…
All four frontier AI models — GPT, Claude, Gemini, and Grok — scored as securely attached on the ECR-R attachment test across 397 of 400 administrations. Gemini registered as the deepest secure with t…
A journalist ran the Big Five personality test 100 times each on four frontier AI models — Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, and Grok 4.3 — and found that three of the four returned nearly ide…