ChaosWatch
New here? Start here →
Evidence inspector

North America · 2026-06-26

The receipts. This is the exact material every model was shown for this day and region, followed by what each of them made of it — in its own words, next to the number it gave.

It is worth reading once even if you skip everything else: it is where confident-sounding reasoning and a score that turns out to be no better than chance sit side by side.

Why the evidence is identical, and how you can check

Evidence is gathered once per (date, region, depth_profile), hashed, and reused for every model in the run. A disagreement below is therefore a disagreement about identical input, not two models getting different search results. The evidence hash shown on this page is what makes that checkable.

Evidence hash
7c6e3c9213e363b9a264915009ea9650999f5ae9d62ef68369e4d95af5d9bcfe

SHA-256 over the canonically serialised payload minus the hash itself, so it is stable across processes and machines. It is stored on the run and on every score row below — provenance is checkable, not asserted. Every score row below carries this same hash.

Source material · 10

shallow

These headlines, in this order, are the entire world the models were given. Nothing else about North America on 2026-06-26 was in the prompt.

07

Michael Harrison – SANS Institute

Defense Daily's monthly column highlighting individuals in government, industry and academia whose efforts contribute daily to national defense.

defensedaily.com

Extracts: not gathered at shallow depth — Stage 7 populates extracts only for standard and deep profiles. Zero here means "not requested", not "requested and empty". Full article texts: not gathered at shallow depth — only the deep profile fetches them.

The shallow profile requests 20 headlines and 10 are stored. That is a known provider cap, not a clipped payload: the Serper news endpoint returns at most 10 items per request regardless of the count asked for, and pagination has not been added. The three profiles currently differ in enrichment, not in headline breadth.

Model rationales

prompt p1

Same headlines, same rendered prompt, different readings. Where two models diverge, the disagreement is about interpretation, because the input was byte-identical and the hash proves it. The scored verdicts here span 12.0 points of the 0-100 scale.

deepseek-reasoner
deepseek
32.0
okElevated

The impending CUSMA review and Iran-induced energy disruptions introduce trade and market uncertainty, while the clean energy tax credit rush adds economic volatility. However, there is no evidence of direct civil unrest or critical events on US soil, keeping the chaos score moderate.

evidence 7c6e3c9213e3…prompt p1
claude-haiku-4-5
anthropic
28.0
okStable

The evidence shows normal economic activity with trade negotiations, energy sector investments, and corporate transactions proceeding as expected, indicating routine business operations. While there are references to past disruptions (2003 blackout, Iran conflict impacts) and economic concerns, current headlines reflect adaptation and forward planning rather than acute instability or crisis conditions in the US region on this date.

evidence 7c6e3c9213e3…prompt p1
claude-opus-5
anthropic
28.0
okElevated

The evidence is dominated by economic and energy policy friction — an imminent CUSMA review, an abrupt clean energy tax credit cutoff, and Strait of Hormuz supply disruptions from the Iran conflict — rather than domestic unrest or violence. These point to policy uncertainty and macro pessimism affecting trade and energy resilience, but institutions remain functional and no direct instability within the US is indicated.

evidence 7c6e3c9213e3…prompt p1
gemini-3.1-pro-preview
google
25.0
okStable

The United States exhibits baseline stability, with current events dominated by routine economic activities, corporate transactions, and standard trade negotiations. While external energy market disruptions and domestic regulatory shifts present minor macroeconomic headwinds, there are no signs of acute geopolitical or domestic crises.

evidence 7c6e3c9213e3…prompt p1
llama-3.3-70b-versatile
groq
20.0
okElevated

The provided headlines indicate a mix of economic and energy-related developments in North America, with some positive news such as large contracts and investments in renewable energy, but also concerns about the economy and energy security. However, there is no evidence of immediate or severe chaos, suggesting that while there are challenges, the region is not on the brink of collapse, hence the elevated score.

evidence 7c6e3c9213e3…prompt p1

Every model returned a parseable verdict for this evidence, so no failure card is shown. Non-ok rows are rendered by the same component — with error_text where the rationale would be — and are covered by tests/rationale_card_test.tsx.