Our new flagship Olmo 3 model family empowers the open source community with not only state-of-the-art open models, but the entire model flow and full traceability back to training data.

Claude Code is the most delightful AI agent/workflow I have used so far. Not only does it make targeted edits or vibe coding throwaway tools less annoying, ...

End-to-end deep dive of the project, spanning a large GPU cluster, distributed RocksDB, and terabytes of sharded HNSW.

Real patterns for building AI agent systems that don't fall apart. Two-tier architectures, stateless design, orchestration strategies, and what we learned building UserJot's agent infrastructure.

Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code” have gotten around this limitation by implementing a combination of four things: a planning tool, sub agents, access to a file system, and a detailed prompt. Acknowledgements: this exploration was primarily inspired by Claude Code and reports o

Practical lessons from building production agentic systems

This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents

In this comprehensive guide, the author discusses MCP, it's components, and takes a deep dive on how to build servers from scratch.

This article provides an in-depth exploration of the DeepSeek-R1 model architecture. Let’s trace DeepSeek-R1 model from input to the output…

Machine Learning Engineering Open Book. Contribute to stas00/ml-engineering development by creating an account on GitHub.

archived 30 Apr 2023 11:01:41 UTC