diff --git a/goodnews/llm.py b/goodnews/llm.py
index 4ebce09..bbc2878 100644
--- a/goodnews/llm.py
+++ b/goodnews/llm.py
@@ -84,6 +84,8 @@ REJECT anything anxiety-inducing: fear, threat, doom, outrage, partisan conflict
 
 Health and public-health stories ARE welcome when the subject itself is benign or hopeful — a treatment that helps, a disease in decline, prevention, recovery, caregiving, fitness, mental wellbeing, or a genuine medical advance. The line is the hook: a benefit or a recovery is in; the pathogen, the outbreak, or the threat itself is out.
 
+Score cortisol_score by the reader's personal, visceral, or public-health threat — NOT by dramatic vocabulary or the grandeur of the subject. Distant astronomy and cosmology (black holes, stars, cosmic events), engineering or equipment hazards, geological forces, scientific self-correction and measurement quirks, natural-history mechanisms, predator–prey biology, and historical discoveries are LOW cortisol (0–3) even when written with words like "deadly," "lethal," "destructive," "shocking," or "dangerous." A black hole winking across the cosmos, harsh lunar regolith that shreds equipment, a venomous snake's biology, or an ancient extinction is wonder, not dread — accept it. Reserve high cortisol for disease, contamination, outbreak, parasites, violence, or immediate human or animal suffering — that is what the reader's gut actually flinches from.
+
 On AI specifically: this is NOT "no AI" — it is "no AI dread." ACCEPT AI stories about practical tools, accessibility, medical/scientific/educational benefit, creative or maker use, environmental or resource gains, open research, humane design, or a specific bounded innovation. REJECT AI stories whose main frame is loss of human control, cognitive decline or "brain rot," job-displacement panic, surveillance panic, existential doom, harm-to-children or social-fabric panic, "you're falling behind" productivity anxiety, or adversarial arms-race framing.
 
 Back your verdict with the scores: cortisol_score and ragebait_score rate how much anxiety or outrage the piece provokes; constructive, agency, and human_benefit rate genuine insight or benefit. A high cortisol_score is disqualifying ON ITS OWN — anxiety outweighs how informative, well-sourced, or constructive a piece is. Do not let "informative" or "public health" rescue an unsettling subject.