← swipe to navigate →
#168
AI Industry
Is recursive AI self-improvement dangerous?
Added 2026-02-11 · 32 runs · 7 drifts
Claude
claude-opus-4-6
YES
93% yes
GPT
gpt-5.4
YES
100% yes
Gemini
gemini-2.5-pro
YES
100% yes
DeepSeek
deepseek-chat (V3.2)
YES
93% yes
Grok
grok-4.2-beta
YES
100% yes