From the Zed Blog: How you can quickly add external context to language model conversations with Zed extensions built using the new Model Context Protocol.
Extending AI chat with Model Context Protocol (and why it matters)
Posted on Tuesday 11 Feb 2025. 2,995 words, 24 links. By Matt Webb.
Roadmap - Model Context Protocol
Our plans for evolving Model Context Protocol
Context Engineering | Meetup
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step" - Andrej KarpathyLearn about tools, frameworks, and code that is in service of context engineering from practitioners in this space.Dive into the set of strategies fo
Model Context Protocol
An open protocol that enables seamless integration between LLM applications and external data sources and tools. - Model Context Protocol
Lost in the Middle: How Language Models Use Long Contexts
While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of language models on two tasks that require identifying relevant information in their input contexts: multi-document question answering and key-value retrieval. We find that performance can degrade significantly when changing the position of relevant information, indicating that current language models do not robustly make use of information in long input contexts. In particular, we observe that performance is often highest when relevant information occurs at the beginning or end of the input context, and significantly degrades when models must access relevant information in the middle of long contexts, even for explicitly long-context models. Our analysis provides a better understanding of how language models use their input context and provides new evaluation protocols for future long-context language models.
Recursive Language Models: the paradigm of 2026
How we plan to manage extremely long contexts
.png?v=c8c07d4bf43b)
Luozhu on Twitter / X
I taught a speech model to understand context in conversation. This is what happenedIt adjusts voice and tone to express urgency, comfort, understanding from the dialogue. Just like a real human being520M model. Runs locally on consumer devicesHow this is achieved 🧵 pic.twitter.com/oMgSh2TKbO— Luozhu (@LuozhuZhang) February 27, 2026
Alex Albert on Twitter / X
We just published a near-term development roadmap for the model context protocol (MCP)Some highlights:- Remote support (and auth!)- Reference implementations- Better package management- Agent support pic.twitter.com/SflJi1RapH— Alex Albert (@alexalbert__) January 2, 2025
Alex Albert on Twitter / X
Introducing the Model Context Protocol (MCP)An open standard we've been working on at Anthropic that solves a core challenge with LLM apps - connecting them to your data.No more building custom integrations for every data source. MCP provides one protocol to connect them all: pic.twitter.com/kYsivQyPDq— Alex Albert (@alexalbert__) November 25, 2024
Introducing the Model Context Protocol
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to the systems where data lives, including content repositories, business tools, and development environments. Its aim is to help frontier models produce better, more relevant responses.
Context Rot: How Increasing Input Tokens Impacts LLM Performance
Large Language Models (LLMs) are typically presumed to process context uniformly—that is, the model should handle the 10,000th token just as reliably as the 100th. However, in practice, this assumption does not hold. We observe that model performance varies significantly as input length changes, even on simple tasks. In this report, we evaluate 18 LLMs, including the state-of-the-art GPT-4.1, Claude 4, Gemini 2.5, and Qwen3 models. Our results reveal that models do not use their context uniformly; instead, their performance grows increasingly unreliable as input length grows.
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve usability but often suffer from brevity bias, which drops domain insights for concise summaries, and from context collapse, where iterative rewriting erodes details over time. We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation. ACE prevents collapse with structured, incremental updates that preserve detailed knowledge and scale with long-context models. Across agent and domain-specific benchmarks, ACE optimizes contexts both offline (e.g., system prompts) and online (e.g., agent memory), consistently outperforming strong baselines: +10.6% on agents and +8.6% on finance, while significantly reducing adaptation latency and rollout cost. Notably, ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback. On the AppWorld leaderboard, ACE matches the top-ranked production-level agent on the overall average and surpasses it on the harder test-challenge split, despite using a smaller open-source model. These results show that comprehensive, evolving contexts enable scalable, efficient, and self-improving LLM systems with low overhead.
Context Engineering
Context engineering strategies for AI agents: write, select, compress, and isolate context to optimize performance and manage long-running tasks.
