Google Deepmind – Bakken & Baeck

Translating technical complexity.

For the VisualisingAI series, we translated two concepts in the evolving AI field—quantum computing and multimodality training—into visuals that stay close to the tech. Capabilities Brand Starting point Google DeepMind's Visualising AI initiative aims to create more diverse and accessible representations of AI by commissioning designers and artists to create new visual interpretations of topical AI concepts. They invited us to interpret two themes particularly relevant within the field of AI today: Quantum Computing and Multimodality Training. While given free rein on content and style,…

saved by

• Jon

related reading

• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• Using Artificial Intelligence to Augment Human Intelligencedistill.pub
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• A Pragmatic Vision for Interpretability — LessWronglesswrong.com
• Feature Visualizationdistill.pub
• Transformer Explainer: LLM Transformer Model Visually Explainedpoloclub.github.io
• Visualizing Algorithmsbost.ocks.org
• The Thinking Game | Full documentary | Tribeca Film Festival official selectionyoutube.com
• 9th Workshop on Visualization for AI Explainabilityvisxai.io
• Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention) – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• The Building Blocks of Interpretabilitydistill.pub
• AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms — Google DeepMinddeepmind.google