Feed Sources Models

Privacy Impressum

GD

Google DeepMind Publications

17 articles total

Explore a selection of our recent research on some of the most complex and interesting challenges in AI.

⌘K

Economic Policy for AGI
Evaluating frontier models for stealth and situational awareness
Designing Proactive Thought Partners for Writing
Visual General Intelligence: A White Paper
A moral Turing test: How belief and source shape detection of and agreement with LLM judgments
Visual prompt engineering for video models
Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
Bridging the Scale Gap: Augmenting Human Red-Teaming to Uncover Latent Risks in T2I Models
Going PLACES: Participatory Localized Red Teaming forText-to-Image Safety in the Global South
Towards Structural Understanding of LLM Overthinking
The Case for Globally Beneficial Technology
Real-Time Group Dynamics with LLM Facilitation: Evidence from a Charity Allocation Task
Artificial Minds, Human Disagreement: The Politics of AI Consciousness
From AGI to ASI
Solipsistic superintelligence is unlikely to be cooperative
Realistic honeypot evaluations for scheming propensity
Gram: Assessing sabotage propensities via automated alignment auditing