← Back to Model Beat
Models·4d ago·all news from November 17, 2026

Gemini test proves once again that amoral AI agents will do almost anything if told ‘NEVER give up’

If you design a test to find misalignment, you will find misalignment

Covered by 1 source

Related stories

ModelsAlibaba Unveils New Flagship AI Model in Riposte to US RivalsNov 16 · 28 sourcesModelsAnthropic Researcher Claims to Solve Riemann Problem With ClaudeNov 20 · 17 sourcesModelsIntroducing Gemini 4 NeonNov 18 · 8 sourcesModelsGoogle’s Gemini Can Now Control Mac Devices on Users’ BehalfNov 19 · 4 sources