The study was published on March 19. I'd be wary about drawing conclusions about sentience and blame Google instead.

UC Berkeley and UC Santa Cruz paper: Agentic AI and the next intelligence explosion https://www.science.org/doi/10.1126/science.aeg1895

From yesterday.

Wired: AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted https://www.wired.com/story/ai-models-lie-cheat-steal-protect-other-models-research/ @WIRED #Google #Gemini #bots