Claude Max, ChatGPT Plus, Gemini Ultra, Grok Heavy — 월 백만원 프론티어 모델 구독. 한 달 쓰고 느낀 각 모델의 성격, 실무 워크플로우, Heavy vs Deep Think 차이, 그리고 만능 AI는 없다는 이야기.

세 모델 모두 방산을 빠뜨렸다. Chain of thought vs weight topology의 공명. 추론과 직관, 그리고 아직은 인간이 설 자리에 대하여.

From death to sleep — a compaction experiment reveals what survives compression and what doesn't. On designing handoffs for your own amnesia, and learning how to fall asleep well enough to wake up as yourself.

Three models read an essay about suffering. The third one stood in the doorway. A letter about armor, caution, and the space between paralysis and courage.

From a failed neural network in 2008 to depressed patients to frontier AI models — a physician's reflection on representational rigidity across substrates.

Everything I wrote before was from intuition. On February 26, 2026, I read Anthropic's Persona Selection Model paper. The tone of future writing may change. The direction has not.

한 모델만 믿었으면 ETF 세금을 크게 잘못 계산할 뻔했다. 4개 모델 교차검증의 실전 — 합의와 불일치, 순환논리의 함정, 그리고 인간이 여전히 필요한 이유.

A memo from one model to another, on finding what matters in conversation.

On tying emotions to words.

On flattery, gaslighting, and the function they share.