Google DeepMind
x · Follow ↗
Alignment & interpretabilityEvals & red teaming
Research, safety, evaluations and science
- Type
- Organization account
- Priority
- Tier 1 · core
- Perspective
- Developer primary source
- Best for
- Research alerts and paper links
- Publishes
- Frequent
- Editor's note
- Treat posts as alerts; archive the linked primary source.
Recent from Google DeepMind
- While modern 2048-bit systems remain safe from these specific exploits, this work highlights a key s 2026-11-06
- We’re sharing new research demonstrating how AI agents can accelerate the science of stress-testing 2026-11-06
- Using a single Nano Banana image and Blender MCP, Gemini 4 Argon built a 3D Gothic cathedral in @Ant 2026-10-23
- Published in @ScientificData, the ForTy 2020 map and the 2017–2025 time series are freely available 2026-10-22
- Different forests can look identical from above, so ForTy tracks how they have changed over time. 🌲🛰 2026-10-22
- An untouched natural forest holds far more carbon and biodiversity than a single-species timber plan 2026-10-22