Code execution with MCP: Building more efficient agents
Direct tool calls consume context for each definition and result. Agents scale better by writing code to call tools instead. Here's how it works with MCP.
Frontier Labs 403 stories
Securing AI supply chains: Cohere’s commitment to model signing
Cohere has implemented model signing for all Cohere Command models hosted on Hugging Face to improve integrity and authenticity efforts.
LFM2-ColBERT-350M: One Model to Embed Them All | Liquid AI
Today, we release LFM2-ColBERT-350M, a late interaction retriever with excellent multilingual performance. It allows you to store documents in one language (for example, a product description…
On-Policy Distillation
On-Policy Distillation by Kevin Lu in collaboration with others at Thinking Machines
The Building Blocks of Agentic AI: From Kernels to Clusters
At PyTorch Conference 2025 in San Francisco, we unveiled five new projects spanning kernel languages, distributed systems, reinforcement learning, agentic frameworks, and edge AI deployment.
Introducing Mistral AI Studio.
The Production AI Platform.
Agentic Robotics at the Edge: Liquid AI, AMD, and Robotec.ai Demonstrate LFM2-VL-3B in Embedded Autonomy | Liquid AI
Together, Liquid AI, AMD, and Robotec.ai have deployed compact foundation models for autonomous agentic robotics: showcasing a specialized 3-billion parameter Liquid vision-language model (LFM2-VL-3B), running efficiently…
How Liquid AI Uses ExecuTorch to Power Efficient, Flexible On-Device Intelligence | Liquid AI
When we needed to deploy our hybrid LFM models on-device, we faced a critical challenge: existing inference engines couldn't handle the unique combination of attention and…
LFM2-VL-3B: A New Efficient Vision-Language for the Edge | Liquid AI
We’re excited to release LFM2-VL-3B, the newest and most capable addition to our family of vision LFMs (450M and 1.6B). Built on the LFM2-2.6B backbone, this…
Beyond permission prompts: making Claude Code more secure and autonomous
Claude Code's new sandboxing features, a bash tool and Claude Code on the web, reduce permission prompts and increase user safety by enabling two boundaries: filesystem…
Equipping agents for the real world with Agent Skills
Claude is powerful, but real work requires procedural knowledge and organizational context. Introducing Agent Skills, a new way to build specialized agents using files and folders.
Announcing the Cohere Partner Program: Boosting enterprise AI
Today, we are proud to announce the launch of the Cohere Partner Program, a new initiative designed to help our partners innovate faster, expand market impact,…
LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts | Liquid AI
We are releasing LFM2-8B-A1B, our first on-device Mixture-of-Experts (MoE) with 8.3B total parameters and 1.5B active parameters per token. By activating only a sparse subset of…
LFM2-Audio: An End-to-End Audio Foundation Model | Liquid AI
LFM2-Audio defines a new class of audio foundation models: lightweight, multimodal, and real-time. By unifying audio understanding and generation in one compact system, it enables conversational…
LoRA Without Regret
LoRA Without Regret by John Schulman in collaboration with others at Thinking Machines
Effective context engineering for AI agents
Context is a critical but finite resource for AI agents. In this post, we explore strategies for effectively curating and managing the context that powers them.
Building AI for Cyber Defenders
We invested in improving Claude's ability to help defenders detect, analyze, and remediate vulnerabilities in code and deployed systems. This work allowed Claude Sonnet 4.5 to…
Introducing Liquid Nanos — frontier‑grade performance on everyday devices | Liquid AI
We’re launching Liquid Nanos — a family of 350M–2.6B parameter foundation models that deliver frontier‑model quality on specialized, agentic tasks while running directly on phones, laptops,…
Expanding xAI for Government with GSA OneGov
Expanding ‘xAI For Government’ with more accessible AI tools for the Federal Government
Cohere adds $100M in second close to latest round as it scales security-first enterprise AI
Additional funding supports our growing global operations and development of frontier enterprise AI technology.
Exploring AI in Education
Using Cohere Grants to transform students into AI builders.
Introducing LFM2-2.6B: Redefining Efficiency in Language Models | Liquid AI
We're excited to announce LFM2-2.6B, the newest and currently largest model in our Liquid Foundation Model 2 series. Building on our 350M, 700M, and 1.2B models,…
Grok 4 Fast
Pushing the Frontier of Cost-Efficient Intelligence
A postmortem of three recent issues
This is a technical report on three bugs that intermittently degraded responses from Claude. Below we explain what happened, why it took time to fix, and…