Unlocking the potential of vision language models on satellite imagery through fine-tuning
Unlocking the potential of vision language models on satellite imagery through fine-tuning
Frontier Labs 403 stories
How Upwork helps freelancers win more work with Llama
Upwork, one of the world’s largest work marketplaces, is using Llama to power Uma, its mindful AI, to help freelancers land jobs faster and more confidently.
Announcing Codestral 25.08 and the Complete Mistral Coding Stack for Enterprise
Announcing Codestral 25.08 and the Complete Mistral Coding Stack for Enterprise
Our contribution to a global environmental standard for AI
Our contribution to a global environmental standard for AI
Joining forces with AWS on a new program to help startups build with Llama
We're joining forces with Amazon Web Services to announce a new program that will provide resources and support to 30 promising startups in the U.S. that…
Le Chat dives deep.
Introducing Deep Research (Preview), plus Audio-in, Projects, and other updates.
Cyber Evaluations of Claude 4
We partnered with Pattern Labs on a range of cybersecurity evaluations of Claude Opus 4 and Claude Sonnet 4, with Opus demonstrating especially notable improvement over…
Project Vend
We let Claude manage an automated store in our office as a small business for about a month. We learned a lot about the plausible, strange,…
Desktop Extensions: One-click MCP server installation for Claude Desktop
Desktop Extensions make installing MCP servers as easy as clicking a button. We share the technical architecture and tips for creating good extensions.
How we built our multi-agent research system
Our Research feature uses multiple Claude agents to explore complex topics more effectively. We share the engineering challenges and the lessons we learned from building this…
Cyber Toolkits for LLMs
Large Language Models (LLMs) that are not fine-tuned for cybersecurity can succeed in multistage attacks on networks with dozens of hosts when equipped with a novel…
Claude Code: Best practices for agentic coding
Claude Code is a command line tool for agentic coding. This post covers tips and tricks that have proven effective for using Claude Code across various…
v0.2.0
Llama 4 Support ( https://www.llama.com )
The "think" tool: Enabling Claude to stop and think in complex tool use situations
A new tool that improves Claude's complex problem-solving performance
v0.1.4
What's Changed fix: do not use python_tag when encoding non-code_interpreter tool_calls by @ehhuang in #283 fix: tool_call was not encoded by @ehhuang in #284 Full Changelog:…
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
SWE-bench is an AI evaluation benchmark that assesses a model's ability to complete real-world software engineering tasks.
Building effective agents
We've worked with dozens of teams building LLM agents across industries. Consistently, the most successful implementations use simple, composable patterns rather than complex frameworks.
Introducing Contextual Retrieval
For an AI model to be useful in specific contexts, it often needs access to background knowledge.
Coordinated Vulnerability Disclosure Dashboard
A regularly updated record of vulnerabilities found by Anthropic and reported to maintainers with cryptographic commitments to each finding at the time of disclosure.