Longterm Wiki

AI Safety

Google DeepMindResearch Areasai-safety

Record Metadata

Record Keyai-safety
EntityGoogle DeepMind
CollectionResearch Areas(4 records total)
SchemaMajor research initiatives and focus areas.
YAML Filepackages/kb/data/things/A4XoubikkQ.yaml

Fields

NameAI Safety
DescriptionResponsible AI development including alignment, robustness, and societal impact
StartedJan 2017
Key Publicationdeepmind.google
NotesFrontier Safety Framework published 2024; safety team includes alignment, interpretability, and ethics researchers

Other Records in Research Areas (3)

KeyNameDescriptionStarted
game-playing-aiGame-Playing AIReinforcement learning for complex games including Go, chess, StarCraft, and DiplomacyJan 2013
protein-structure-predictionProtein Structure PredictionDeep learning for predicting 3D protein structures from amino acid sequencesJan 2016
neuroscience-inspired-aiNeuroscience-Inspired AIUsing insights from neuroscience to improve AI architectures and learning algorithmsSep 2010
Record: ai-safety | Longterm Wiki