Contextual Retrieval(anthropic.com)

287 points by loganfrederick 2 years ago | 70 comments

Claude 2.1(anthropic.com)

492 points by technics256 2 years ago | 297 comments

Anthropic's announcement post introducing Claude 2.1, a new version of its Claude large language model, dated November 21, 2023.

Claude 3 model family(anthropic.com)

920 points by marc__1 2 years ago | 601 comments

Anthropic's announcement post introducing the Claude 3 model family, its next generation of Claude AI models.

Donating the Model Context Protocol and establishing the Agentic AI Foundation(anthropic.com)

273 points by meetpateltech 10 months ago | 123 comments

Decomposing language models into understandable components(anthropic.com)

402 points by tompark 3 years ago | 58 comments

Anthropic research post from Oct 2023 on decomposing language model neurons into more interpretable features.

MCP vs. API Explained(norahsakal.com)

150 points by typhon04 1 year ago | 92 comments

I still prefer MCP over skills(david.coffee)

413 points by gmays 6 months ago | 335 comments

A blog post arguing that the Model Context Protocol (MCP) is preferable to agent skills for extending LLM tools.

OpenAI adds MCP support to Agents SDK(openai.github.io)

766 points by gronky_ 1 year ago | 238 comments

OpenAI Agents SDK documentation page describing support for Model Context Protocol (MCP) servers to provide tools and context to agents.

Context Language Models(arxiv.org)

164 points by emersonmacro 25 days ago | 44 comments

arXiv paper introducing Context Language Models, LLMs that natively manage their own context by treating it as an editable file, with benchmarks on agent tasks.

100K Context Windows(anthropic.com)

853 points by samwillis 3 years ago | 364 comments

Anthropic announcement from May 11, 2023 introducing 100K token context windows for its Claude language model.

MCP: An (Accidentally) Universal Plugin System(worksonmymachine.substack.com)

729 points by Stwerner 1 year ago | 322 comments

A Substack essay by Scott Werner arguing that Anthropic's Model Context Protocol works as an accidental universal plugin system, using a USB-C analogy.

AI models may be capable of self-replicating without access to a datacenter(anthropic.com)

36 points by artninja1988 13 days ago | 26 comments

Anthropic Frontier Red Team post reporting experiments suggesting small AI models may soon self-replicate on commercial IoT devices without datacenter access.