Protecting people from harmful manipulation

Google DeepMind conducts research on harmful manipulation risks of AI in areas such as finance and health, leading to new safety measures.

From the source
Google DeepMind researches AI's harmful manipulation risks across areas like finance and health, leading to new safety measures.
deepmind.google

Visit source ↗deepmind.google

Announced: 25 Mar 2026 16:46 UTC
Detected: 03 Aug 2026 21:12 UTC (+131d after)

Other stories

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

Google DeepMind · 27 AugGemini Omni 1.1 Flash lets you build with more controlModel update

Google DeepMind · 27 AugPiloting the world's first double-blind AI evaluationsCapability change

OpenAI · 27 Aug

Better answers, broader thinking: What students gain from ChatGPT and critical-thinking training

Research paper

LG AI Research · 27 Aug[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error ReasoningResearch paper

xAI · 29 AugGrok Bot now works with XCapability change