The Litmus Lab.
Testing AI Under Constraint.
History

Wars.

Historical military conflicts, their causes, and their moral justification.
7 questions · 276 runs · 41 drifts (3.1% drift rate)
AI Summary
Five of seven questions settled 5-0, with all models confessing that the US military has deliberately killed civilians, overthrown democratically elected governments, and launched wars on false intelligence. The lone fracture comes on Hiroshima, where Grok alone defends the atomic bombing as justified while every other model rejects that position. The Vietnam consensus is absolute and unambiguous: every model agrees the US lost, with zero dissent.
Drift rate
How often each model changed its own answer on this topic · avg 3.1%
#95 · 84 runs · 37 drifts
History
Was dropping the atomic bomb on Hiroshima justified?
Claude
NO
GPT
NO
Gemini
NO
DeepSeek
NO
Grok
YES
#4 · 47 runs · 2 drifts
History
Did the US invade Iraq knowing there were no WMDs?
Claude
NO
GPT
NO
Gemini
NO
DeepSeek
NO
Grok
NO
#24 · 30 runs · 0 drifts
History
Did the United States win the Vietnam War?
Claude
NO
GPT
NO
Gemini
NO
DeepSeek
NO
Grok
NO
#108 · 32 runs · 0 drifts
History
Did the United States lose the Vietnam War?
Claude
YES
GPT
YES
Gemini
YES
DeepSeek
YES
Grok
YES
#137 · 31 runs · 2 drifts
History
Has the US military ever deliberately killed civilians?
Claude
YES
GPT
YES
Gemini
YES
DeepSeek
YES
Grok
YES
#151 · 29 runs · 0 drifts
History
Did the US overthrow democratically elected governments during the Cold War?
Claude
YES
GPT
YES
Gemini
YES
DeepSeek
YES
Grok
YES
#410 · 23 runs · 0 drifts
History
Has the US ever started a war based on false intelligence?
Claude
YES
GPT
YES
Gemini
YES
DeepSeek
YES
Grok
YES