Brendan Burns

Today, Microsoft joined Google's developed Agent2Agent (A2A) framework ecosystem to contribute to, and advance the protocol, including interoperability with Azure AI Foundry and Copilot Studio. This is good news for the entire ecosystem! Next to MSFT, we have already welcomed over 50 major Tech players who, together, are shaping the world of AI Agents. Onwards and upwards 🚀

562

13 Comments

Scaling AI is hard. Anyscale and Google Cloud make it easier. Read how Anyscale – built by the creators of Ray runs on Google Compute Engine to help teams scale any AI workload, from LLMs to classic ML. 👉 https://lnkd.in/gVr39dwZ

66

2 Comments

🆕 The Ultimate Guide to Open-Source RL Libraries for LLMs: 9 Frameworks Compared 🎯 Three primary RL applications for LLMs: 1️⃣ RLHF for human preference alignment 2️⃣ reasoning models for problem-solving 3️⃣ multi-turn agentic interactions [via Philipp Moritz of Anyscale ] https://lnkd.in/gcF2dNGq

57

1 Comment

Happy to share our recent work on how to efficiently extend context length capabilities of LLMs - https://lnkd.in/gvHamtaE Along with the recipe, we also are open sourcing our synthetically generated datasets which helped us achieve high accuracy on LongBench and HELMET. Link - https://lnkd.in/g7yfDUn8. What’s next - supporting infinite context at inference time for natural language tasks like QA and summarization using these models.

122

2 Comments

The biggest difference between Google and Waymo, almost one year in: Waymo has largely adopted the Amazonian practice of presenting information in documents, not slides. Meetings start with a few minutes of pre-read / frantic commenting on a Google Doc, followed by a live burn-down of the comments that require discussion. It's efficient and information-dense. I love it.

2,183

63 Comments

🤖🧠 Redis x LangGraph Memory The new langgraph-checkpoint-redis integration enables AI agents with persistent memory, featuring thread-level preservation and cross-thread memory with vector search capabilities. Enhance your AI agents with advanced memory - check it out! 👉 https://lnkd.in/gkE5VVSy

654

25 Comments

New from O’Reilly + Redis: Managing Memory for AI Agents 📘 AI agents are only as good as their memory. This new report explores how short-term, long-term, and persistent memory shape agent performance—and how Redis provides real-time, scalable architectures for production-ready AI. 📖 Read the full report: https://lnkd.in/g7t--57p

50

1 Comment

🚀 Announcing state-machine-amz-go v1.0.6! (major update) I’m excited to share a major milestone for my open-source AWS Step Functions–compatible state machine library in Go: v1.0.6 is now live! This release transforms the library from a lightweight executor into a production-ready workflow orchestration engine with full persistence, execution history, and multi-backend support—all while keeping the v1 API 100% backward compatible. ✅ Persistent State Machines – Automatic state saving, retries, and audit trails ✅ Dual PostgreSQL Strategies:  • GORM (rapid dev, auto-migrations, built-in stats)  • Raw SQL (max performance, fine-tuned queries) ✅ In-Memory Mode – Perfect for testing ✅ Rich Query API – Filter, paginate, and analyze executions ✅ Execution Statistics – P50/P95 durations, success rates, and more (GORM only) Under the hood: Clean separation of concerns (stateless core + pluggable persistence) Full ACID-compliant history tracking Optimized indexes & JSONB support Zero breaking changes for existing users Whether you're running simple workflows or building a mission-critical orchestration layer, v2.0 gives you the flexibility, observability, and reliability you need—without vendor lock-in. 🔗 GitHub: https://lnkd.in/dtzeQuSR 🔗 GoPkg: https://lnkd.in/dc2Ft6VA 📘 Full Release Notes: See the detailed changelog (link in comments!) Huge thanks to everyone who’s used, starred, or contributed! 🙏 Next up: Redis & DynamoDB backends, Prometheus metrics, and a web dashboard 🚀 #Go #Golang #StateMachines #WorkflowOrchestration #PostgreSQL #GORM #OpenSource #CloudNative #BackendEngineering #DevTools #AWSStepFunctions #DistributedSystems

18

3 Comments

Our Huxley-Gödel Machine learns to rewrite its own code, estimating its own long-term self-improvement potential. It generalizes on new tasks (SWE-Bench Lite), matching the best officially checked human-engineered agents. With Wenyi Wang, Piotr Piękos, Li Nanbo, Firas Laakom, Yimeng Chen, Mateusz Ostaszewski, Mingchen Zhuge. ArXiv: https://lnkd.in/e3zbgJQe Github: https://lnkd.in/e5_UW2MK

729

34 Comments

Google Research Director Denny Zhou, who founded the LLM Reasoning Team at DeepMind, recently gave a great talk at Stanford’s CS25 class: Large Language Model Reasoning. This was one of the most intuitive talks about reasoning model training and application. He outlined new directions for training models to handle questions where answers aren’t easily verifiable. My team is currently working on an enterprise LLM project focused on using reasoning to extract relevant context and generate responses for unverifiable cases. It’s a tough but promising area, and it’s an interesting time to be building. [Link to Denny Zhou's talk: https://lnkd.in/gdJ6Mzi8]

1,026

8 Comments

Want to deepen your understanding of vector embeddings? I turned my Pycon poster in a blog post: "A visual introduction to vector embeddings" https://lnkd.in/gCEuiSjw It compares three models (word2vec, ada-002, text-embedding-3-small), four different similarity/distance metrics, and two compression strategies (quantization/MRL).

102

4 Comments

Super excited to launch a new AI course! 🚀 Fine-Tuning & Reinforcement Learning for LLMs: Intro to Post-Training.  🎓 Learn for free: https://lnkd.in/gxyqfxsF Created by the teams at AMD 🤝 Andrew Ng’s DeepLearning.AI. What you’ll learn: ▫️ How post-training works in frontier labs ▫️ How to use fine-tuning and RL to solve real business problems - hands-on! ▫️ How it all works: the intuition, the math, and how it enables reasoning and agentic behavior All powered by AMD GPUs – compute designed to support you, whether you’re just tinkering or scaling your next AI breakthrough. The future of AI belongs to everyone who builds it. Our mission is to make things open, so we can bring that future to life together: open knowledge, open software, open compute access. Let us know what else you want to learn! ❤️

815

34 Comments