Bayesian Threat Board?How this worksEvery tracked threat has a current probability that moves with evidence. Each dispatch we ingest is scored against every threat; if it raises or lowers the odds of that threat materializing, it nudges the probability via Bayesian update (prior + evidence → posterior).
Confidence intervals tighten as evidence count grows. Not forecasting — continuous re-weighting of a claim against all available reporting.
Confidence intervals tighten as evidence count grows. Not forecasting — continuous re-weighting of a claim against all available reporting.
Every threat we’re tracking.
10 threats · 464,852 pieces of evidence contributing · 0 at ≥70% probability. Click any row for the full evidence stream + probability history.
10 threats shown
- 01North Korea provocationsnuclearNorth Korea· 7,200 evidence69CI 68–70%→ +1.3pp7dModerate
Detail → - 02Sudan humanitarian collapsehumanitarianSudan· 8,179 evidence68CI 67–69%↓ ±0.0pp7dModerate
Detail → - 03Global food crisishumanitarian· 13,345 evidence66CI 65–67%↑ +7.9pp7dModerate
Detail → - 04Middle East regional war expansionconflictIranIsraelLebanonYemen· 196,874 evidence64CI 64–64%↓ -3.3pp7dModerate
Detail → - 05Iran nuclear escalationnuclearIran· 139,930 evidence64CI 64–64%→ +0.4pp7dModerate
Detail → - 06Global recessioneconomic· 9,974 evidence62CI 61–63%↓ -8.7pp7dModerate
Detail → - 07Rare earth supply disruptioneconomicChina· 20,690 evidence57CI 56–57%→ -0.8pp7dModerate
Detail → - 08AI governance crisistechnology· 4,269 evidence53CI 51–54%→ -1.8pp7dModerate
Detail → - 09China-Taiwan military actionconflictChinaTaiwan· 26,554 evidence41CI 40–42%↑ +4.4pp7dModerate
Detail → - 10Russia-Ukraine ceasefireconflictRussiaUkraine· 37,837 evidence17CI 16–17%↑ +9.1pp7dStable
Detail →
Methodology
Each tracked threat begins with a prior probability based on historical base rates and expert elicitation. New evidence — every dispatch scored against the threat — nudges that probability up or down. Bayesian posterior updates compound; confidence intervals tighten as evidence accumulates.
Read the full approach at /about/methodology. Individual threat pages show the full evidence stream including direction, magnitude, and the reasoning our AI engine used for each nudge.