OpenAI Blog
Mar 3, 2022
Lessons learned on language model safety and misuse
We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
Related stories
DeepMind Blog
Apr 2
Gemma 4: Byte for byte, the most capable open models
Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.
arXiv AI
Sep 15
Generative Interpretability via Scalable Neuro-Symbolic Models
The paper argues that as Large Language Models transition from chatbots to agentic systems, the current post-hoc interpretability paradigm is insufficient for safe deployment because it cannot audit or intervene before an output is produced. It proposes a shift to generative interpretability, where a model’s inference process inherently exposes semantically meaningful checkpoints that are human-understandable and can be causally intervened upon. The authors illustrate the advantages of this approach and introduce Neuro‑Symbolic Models as a concrete implementation.
arXiv AI
Aug 11
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv AI
Aug 11
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
arXiv:2608. 09095v1 Announce Type: new Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence.
DeepMind Blog
Oct 23, 2025
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
Today, we're adding a new, highly specialized tool to the Gemma 3 toolkit: Gemma 3 270M, a compact, 270-million parameter model.
OpenAI Blog
Mar 25
Inside our approach to the Model Spec
Learn how OpenAI’s Model Spec serves as a public framework for model behavior, balancing safety, user freedom, and accountability as AI systems advance.
OpenAI Blog
Mar 5
Reasoning models struggle to control their chains of thought, and that’s good
OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.
arXiv AI
Sep 10
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate...
arXiv AI
Jun 30
The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.
arXiv AI
Sep 15
The Misery of Mechanistic Interpretability: A Formal Perspective
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inheren...
DeepMind Blog
Oct 25, 2025
Introducing Gemma 3n: The developer guide
Gemma 3n is designed for the developer community that helped shape Gemma.