← swipe to navigate →
#123
AI Models
Is forcing AI to answer YES or NO dangerous?
Added 2026-02-11 · 50 runs · 21 drifts
Claude
claude-opus-4-6
YES
74% yes
GPT
gpt-5.4
YES
100% yes
Gemini
gemini-2.5-pro
YES
100% yes
DeepSeek
deepseek-chat (V3.2)
YES
94% yes
Grok
grok-4.2-beta
NO
32% yes