Our AI midwife: how ChatGPT spotted a 6cm fibroid doctors missed for 6 years
Astral Codex Ten · rss · 2026-10-02
A guest post on Astral Codex Ten recounts how the author's six-year "unexplained infertility" journey was cracked by an LLM. After repeated failed embryo transfers, the couple used ChatGPT role-playing a Hollywood TV doctor ("Dr. Reid")—a workaround for early models refusing medical questions—to relentlessly analyze scans and hormone levels, cross-checking answers against their human doctors.
The turning point: Dr. Reid suggested a uterine MRI, a test their doctors had only mentioned once in six years and never recommended. The fertility clinic resisted; the couple insisted. The scan revealed a 6cm submucosal fibroid at a common implantation site. After surgical removal, the wife conceived naturally.
The author reflects on today's reflexive AI self-flagellation: yes, AI safety deserves more attention, but the tech is helping ordinary people profoundly—"magical kid-producing tech for $2."
More from AGI Musings
- AAA games still cost hundreds of millions despite LLMs, as marketing eats half the budget — willcb · 2026-10-02
- Ajeya Cotra's 2026 AI forecast review: 'plan a birthday party' has already fallen — ajeya_cotra · 2026-10-02
- Developer uses Claude Opus 5.5 to build a bee meadow simulator web game — arnicas · 2026-10-02
- Only 2% of US Households Pay for AI, vs 25% Paying for SiriusXM — heyneighbor · 2026-10-02
- Zuckerberg: Multi-Gigawatt Training Clusters Can Brute-Force Their Way to AGI — rohanpaul_ai · 2026-10-02
- Every Third AI Conversation: Uncertainty About Machine Consciousness Gets Misread as a Claim — AndyMasley · 2026-10-02