Comprehensive Taxonomy of LLM Hallucinations Nice report covering common hallucinations, root causes, and mitigation strategies.

Connected Component Forest for fraud detection: events are linked chronologically to preserve real-time causality and avoid information leakage in ML pipelines. The result? Time-aware graphs track connections as they form. Master fraud detection with Pierre Halftermeyer's

We released two open-weight reasoning models—gpt-oss-120b and gpt-oss-20b—under an Apache 2.0 license. Developed with open-source community feedback, these models deliver meaningful advancements in both reasoning capabilities & safety. openai.com/index/introduc…

👐Use gpt-oss with `deepagents` Deep Agents require good tool calling capabilities... something that OpenAI's new open source model is pretty good at Thanks to Ryan Eggleston for adding an example how to use gpt-oss (via ollama) to `deepagents` Docs: github.com/hwchase17/deep…

Equip your agent with different subsets of tools throughout a run with dynamic tool selection in LangGraph!

Excited to bring OpenAI’s gpt-oss models to Azure AI Foundry and to Windows via Foundry Local. It’s hybrid AI in action: mix and match models, optimize for performance and cost, and meet your data where it lives. azure.microsoft.com/en-us/blog/ope…

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.

Launching Memori — the open‑source memory layer for AI agents 🧠 SQL‑first. Multi‑agent. Conscious + Auto + Combined modes. Works with CrewAI, Agno, OpenAI, Anthropic & more. ⭐ Try it → github.com/GibsonAI/memori Feedback welcome! #AI #OpenSource #LLM

I'm thrilled to announce the definitive course on Claude Code, created with Anthropic and taught by Elie Schoppik Elie Schoppik. If you want to use highly agentic coding - where AI works autonomously for many minutes or longer, not just completing code snippets - this is it.

🆕 Releasing our entire Agent Reliability track! ft. - Tanmai Gopal (Hasura/PromptQL) - dex (HumanLayer/Context Engineering) - Preeti Somal (Temporal) - Anish Agarwal et al (@Traversal_ai) - Chau Tran (Glean) - Sam Bhagwat (Mastra) - Itamar Friedman (Qodo) Agents are very hyped, but not

Just noticed this getting on the treadmill … gpt 5 today. Hmmm

Today marks a major milestone: GPT-5 is now live in Microsoft 365 Copilot and Copilot Studio! This unlocks a new level of capability for our customers—faster responses, deeper context, and more advanced reasoning. Learn more in our blog: microsoft.com/en-us/microsof…

Looking forward to having a diverse group of speakers for #AgentCon in Boston. Let me, Jason Haley or Bill Wilder know if you have any questions 🙂

📚 🛠️ Agent Reliability A practical guide to help you catch hallucainations, verify groundedness, and monitor tool usage for LangChain/LangGraph applications: docs.futureagi.com/cookbook/cookb…

Beautiful summer morning in the Boston area!

Apple just released Embedding Atlas: An open-source visualization tool for your embeddings. I just gave it a quick spin with some data stored in my vector database. These are my first impressions: - Nice exploration UX with hover and tool tip for single data points - Shows you

AI Ready Apps: From RAG to Chat – Interacting with SQL Database in Microsoft Fabric using GraphQL and MCP blog.fabric.microsoft.com/en-GB/blog/ai-…

"Just fine-tune your embeddings" they said. "It'll fix your RAG system" they said. They were wrong. Here's what actually works: After working with countless retrieval systems, I've noticed a pattern: teams often jump straight to fine-tuning when their vector search

BOOK TOUR SCHEDULE Events with Laz, book signings, talks, giveaways - The Endurance Artist is on the road this fall. LINK: 8020books.com/meet-lazarus-l…

📚LangChain Academy: Deep Research One of the most popular use cases for agents is "deep research" We've added a new hour long course on how to build one of these Course: academy.langchain.com/courses/deep-r…