A reminder to the news media: “conflicting accounts” is what you say BEFORE the incontrovertible video evidence appears. After that, your job is to ask why one side is lying, not to repeat the lie and pretend no one knows the truth.

Claude Code trying to write elisp and counting parentheses

The last 6 months of 2025 were a defining era for MLflow! 🚀 ✅ 𝟭𝟰 𝗥𝗲𝗹𝗲𝗮𝘀𝗲𝘀: Focused on LLM Agentic observability, evaluation, & scalability ✅ 𝗡𝗲𝘄 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: GenAI evaluation, unified tracing & more ✅ 𝗖𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆 𝗚𝗿𝗼𝘄𝘁𝗵: 23 Ambassadors across 17 countries Dive in ➡️ www.linkedin.com/pulse/celebr...

Wrote up a short post on how I use registers to save window configurations in #emacs. It's simple, but it's something I've used daily since discovering it. www.danliden.com/posts/202511...

Good things are possible and we don’t have to settle.

Playing around with #emacs org-mode tables. I ultimately want an easy system where I can use capture templates to easily log new rows of data to tables in particular buffers/files.

Every so often I rediscover the immense usefulness of registering window configurations in #emacs . <C-x r w> to register the configuration, navigate away, return with <C-x r j>. Much easier than trying to reconstruct a complicated window arrangement after e.g. deleting windows.

Use AI to debug AI! 👏 With MLflow 3.4’s MCP server, Claude can query MLflow traces to compare runs and identify issues. @danliden.com’s post covers setup and examples in minutes. Learn more: www.danliden.com/posts/202510... #opensource #mlflow #oss #MCP #claude

Ready to dive into #MLflow? 🚀 Join our text-based LIVE AMA with Danny Chiao & @danliden.com after Danny's MLOps World | GenAI Summit lightning talk! 🗓️ Oct 9 | 1–3pm CT 📍MLflow Slack | #General channel 🔗 RSVP: luma.com/liveama-slac... #opensource #oss #genai #mlops #llmops

Enjoyed this post by @matthewsanabria.dev on Taste and AI: matthewsanabria.dev/posts/you-ha... As the post notes—there's been a lot of discussion about the role of taste when working with AI & the idea that some notion of "taste" is what gives humans an edge. It's important with or without AI!

MLflow has added an MCP server in the most recent release, MLflow 3.4.0. You can e.g. use natural language to find and diagnose failing agent traces w Clauded Desktop. This is a huge step toward making MLflow a tool usable by agents. Blog on setting this up coming soon. #mlflow #ai #agents

I revamped my built-with-emacs personal website and finally finished the second part of my MCP getting started guide, clearing out the drafts backlog. I think the site is looking pretty nice now! www.danliden.com/posts/202509...

Seems like this is a common experience at this point—I ran into an issue where Claude Code was struggling, switched to Codex and was able to resolve it quickly. But the UX of codex is much worse in its present form. Still—really incredible to have have both these tools to work with right now!

🚀 Join the next MLflow Community Meetup on Oct 1 at 4PM PT! 🔹 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗦𝗺𝗮𝗿𝘁𝗲𝗿 𝗘𝘃𝗮𝗹𝘀 𝘄𝗶𝘁𝗵 𝗧𝗿𝗮𝗰𝗲-𝗔𝘄𝗮𝗿𝗲, 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸-𝗔𝗹𝗶𝗴𝗻𝗲𝗱 𝗝𝘂𝗱𝗴𝗲𝘀 🔹 𝗞𝗲𝗲𝗽𝗶𝗻𝗴 𝗘𝘃𝗮𝗹 𝗗𝗮𝘁𝗮𝘀𝗲𝘁𝘀 𝗥𝗲𝗹𝗲𝘃𝗮𝗻𝘁 𝗮𝘀 𝗬𝗼𝘂𝗿 𝗔𝗽𝗽 𝗖𝗵𝗮𝗻𝗴𝗲𝘀 Bring your questions about dataset management, evaluation workflows! ✅ RSVP 👉 luma.com/mlflow-1001 #opensource #oss

The first-ever Open Lakehouse + AI Meetup in Amsterdam was a huge success! 🙌🇳🇱 The evening brought together the open source and data engineering community to explore the latest advancements in open lakehouse and AI architectures. 🚀

📣 MLflow 3.3.0 is now available! This release introduces several major features and improvements: 🔹 𝗠𝗼𝗱𝗲𝗹 𝗥𝗲𝗴𝗶𝘀𝘁𝗿𝘆 𝗪𝗲𝗯𝗵𝗼𝗼𝗸𝘀 🔹 𝗔𝗴𝗻𝗼 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗼𝗻 🔹 𝗚𝗲𝗻𝗔𝗜 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗢𝗦𝗦 🔹 𝗥𝗲𝘃𝗮𝗺𝗽𝗲𝗱 𝗧𝗿𝗮𝗰𝗲 𝗧𝗮𝗯𝗹𝗲 𝗩𝗶𝗲𝘄 🔹 𝗙𝗮𝘀𝘁𝗔𝗣𝗜 + 𝗨𝘃𝗶𝗰𝗼𝗿𝗻 𝗦𝗲𝗿𝘃𝗲𝗿 🔗 Check out the release notes: github.com/mlflow/mlflo... #oss

📣 MLflow Office Hours — Wednesday, Sept 10 Connect directly with #MLflow maintainers and contributors for live Q&A! Bring your production challenges or your latest #LLM and #GenAI experiments—this session is dedicated to hands-on technical discussion and feedback. Save your spot ➡️ lu.ma/mlflow-910

My #Emacs Elevaror Pitch (#August #Blog #Carnival): Me: Have you heard of Emacs? Me: On the surface, it looks like a text editor… xenodium.com/emacs-elevat...

Anyone regularly use #emacs ediff? I just used it to work through a (simple) merge conflict and it was quick and easy, but I've never really invested the time to seriously learn it. Worthwhile?

As OCR + transform can really shave effort from grunt work. An example xenodium.com/a-platform-t...

Join us for the next MLflow Community Meetup! 🥳 This month, we’re excited to bring you the latest updates and insights from the MLflow ecosystem, featuring: ​🔔 Webhooks in MLflow 🧪 Managed MLflow Features Now in OSS 📅 August 20 @ 4:00 PM PT 📍 Live on X, YouTube, & LinkedIn 🔗 RSVP: lu.ma/mlflow820

🎥 Watch our latest meetup for a deeper dive on MLflow 3.2 → www.youtube.com/watch?v=Vtr4... #opensource #mlflow #oss #linuxfoundation

MLflow 3.2 is here! 🚀 Key updates include: 🔹 𝗧𝘆𝗽𝗲𝗦𝗰𝗿𝗶𝗽𝘁 𝗦𝗗𝗞 𝗳𝗼𝗿 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 🔹 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗞𝗲𝗿𝗻𝗲𝗹 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 🔹 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗲𝗱 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 𝗟𝗼𝗴𝗴𝗶𝗻𝗴 🔹 𝗘𝘅𝗽𝗲𝗿𝗶𝗺𝗲𝗻𝘁 𝗨𝗜 𝗥𝗲𝗳𝗿𝗲𝘀𝗵 🔹 𝗧𝗿𝗮𝗰𝗲 𝗨𝗜 𝗘𝗻𝗵𝗮𝗻𝗰𝗲𝗺𝗲𝗻𝘁𝘀 🔹 𝗣𝗜𝗜 𝗠𝗮𝘀𝗸𝗶𝗻𝗴 𝗶𝗻 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 🔹 𝗣𝗼𝗹𝗮𝗿𝘀 𝗗𝗮𝘁𝗮𝗙𝗿𝗮𝗺𝗲 𝗟𝗼𝗴𝗴𝗶𝗻𝗴 🔗 Check out the full release notes → github.com/mlflow/mlflo... #oss

Looking forward to this session! MLflow 3 has introduced some fantastic tools for GenAI Evaluation and observability and Yuki is an excellent speaker on this topic.

I updated my note on how to use Emacs for Python development with a couple of new sections: - Using Python in org-babel - Using a src file + REPL development approach for Python in emacs www.danliden.com/notes/202411... I would love to hear how others use Emacs for Python! #emacs #python

"I think we need more tools like Magit: things like lazygit, lazydocker, tldr, LSP, etc. all extend users’ understanding of systems whilst not keeping them too far from the source." Great post by Ashton Wiersdorf. I hadn't thought of Magit that way before. lambdaland.org/posts/2025-0...

Boost observability in your #GenAI workflows with #MLflow Tracing! 🚀 In this hands-on session, @danliden.com shows how to set up tracing, organize data, work with multiple providers, and debug complex agent workflows. 🎥 Watch the full tutorial: www.youtube.com/watch?v=X5P-... #opensource #oss

Well worth reading if you use MLflow and work with image datasets!

MLflow Tracing is a powerful feature designed to enhance #LLM observability in your #GenAI applications by capturing detailed information about the execution of your application's services. 🙌 (1/4) ... ⤵️

💙 70,000 strong and growing on LinkedIn! Huge thank you to our amazing users, contributors, and #opensource community for following the journey of MLflow and making #MLflow what it is today! From tracking experiments to powering production models, the community makes it all possible.

Join us for the next 𝗠𝗟𝗳𝗹𝗼𝘄 𝗖𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆 𝗠𝗲𝗲𝘁𝘂𝗽 on Wednesday, June 25! 🎉 This month’s meetup features a deep dive into how Amazon SageMaker integrates with #MLflow to streamline the machine learning lifecycle at scale. 🚀 🗓️ June 25 🕓 4:00PM PT 📍 LIVE on LinkedIn, YouTube, & X 🔗 RSVP: lu.ma/6x9kdnd8

This is a great chance to connect with the MLflow community, ask questions, and see how others are building with open source MLOps tools. What would you like to learn about SageMaker + MLflow? 👇

One of Chicago's favorite movie palaces is expanding. 🍿 blockclubchicago.org/2025/05/29/m...

🚀 Build trustworthy generative AI agents with LangChain LangGraph, Amazon SageMaker AI, and #MLflow! Trace behavior, log metrics (including RAGAS), and manage versions with built-in governance to move from testing to production with confidence. Learn more 👉 aws.amazon.com/blogs/machin... #oss

🎥 The recording for "Building Reliable AI Systems with MLflow" is now live! Learn how to use MLflow tracing, evaluation, custom models, and deploy on #Databricks. Simplify complex GenAI projects! Watch now: maven.com/p/af7339 #opensource #oss #mlflow

Curious about improving #LLM trustworthiness? 🤔 Check out how Cleanlab's Trustworthy Language Models (TLM) integrates with #MLflow! TLM analyzes both prompts and responses to flag potentially untrustworthy outputs-no ground truth labels required. 🔗 Learn more: mlflow.org/blog/tlm-tra... #oss

Live from Data Innovation Summit in Stockholm 🇸🇪 MLflow Ambassador Thor Steen Larsen is demoing how #MLflow streamlines image dataset tracking at the #Databricks booth! 🙌 He’s showcasing experiment tracking with dataset artifact logging & MLflow’s @hf.co dataset module. #opensource #huggingface

A Chicago Pope implies the existence of an MLA Pope and APA Pope

Live from NYC 🚀🙌 @danliden.com talks about MLflow for #AgentOps at AI Agent Conference 2025 - bridging the gap between #MLOps and AgentOps with tools to streamline high-quality agent development. #aiagent #mlflow #oss #opensource

🚨 Happening tomorrow — April 30 at 20:00 CET! Join Başak Tuğçe Eskili, Maria Vechtomova, and #MLflow contributor @danliden.com for a lightning session on: 🔹 MLflow Tracing 🔹 MLflow Evaluation 🔹 Deploying AI apps on Databricks 👉 Register: maven.com/p/af7339/bui... #opensource #oss #mlops

On April 23rd, the #MLflow team at Databricks had the opportunity to join a meetup for Bilibili Group - one of the most popular media platforms in China, referred to as "China's YouTube". 🙌 👇 Keep reading! #opensource #genai

📣 Happening tomorrow — Tuesday, April 29 at 4PM PT! Don’t miss MLflow Office Hours: an open Q&A with MLflow maintainers and contributors. 🚀 Bring your questions on model management, LLM workflows, new features, and get direct feedback from the team behind MLflow! 🙌 🔗 Register now: lu.ma/mlflow430

Join us for the next MLflow Office Hours on Tuesday, April 29, for an open Q&A session with MLflow maintainers and contributors! 🚀 This is your chance to get direct, technical feedback from the team behind the project. 🙌 Bring your questions — and let’s talk #MLflow. 😄 RSVP ➡️ lu.ma/mlflow430

Explore how #MLflow Tracing enhances observability in #GenAI applications! 🙌 In this video, @danliden.com provides a hands-on demonstration of setting up MLflow Tracing and discusses its benefits for debugging, experimentation, and data organization. 🎥 Watch now: youtu.be/X5P-zvGGE0g?... #oss

Whether you’re tuning a prompt or training a model, MLflow helps you understand what’s happening under the hood — so you can iterate faster and build better. ✅ MLflow documentation ➡️ mlflow.org/docs/latest/... #mlflow #dspy #opensource #oss

MLflow now supports tracking for #DSPy (Community) optimization — just like it does for @pytorch.org training! 🙌 #MLflow is the first to bring full visibility into DSPy’s prompt optimization process. More observability, less guesswork. Get started today! ➡️ medium.com/@AI-on-Datab... #opensource

🚀 Excited to see the launch of Core4AI from Rahul Pandey, MLflow Ambassador! Core4AI is a powerful new tool that integrates with #MLflow to streamline prompt engineering. 👉 GitHub Repo: github.com/iRahulPandey... 👉 PyPI: pypi.org/project/core... #opensource #llm #promptengineering

🚀 MLflow Office Hours are back! Join us on April 16 at 8AM PT for a special edition: MLflow 3.0 Office Hours! 🙌 Have #MLflow questions? Bring them all! Whether it’s about MLflow 3.0 or anything else MLflow-related, we’re here to help. 🔥 Register today! ➡️ lu.ma/mlflow3.0off... #opensource #oss

Join us for the next MLflow Community Meetup — Wednesday, April 23 at 4PM PT! 🗓️ 🔹 Explore the new MLflow + #DSPy integration 🔹 Learn how Cleanlab adds trust to AI workflows with MLflow 💬 Live Q&A + demos 📺 Streamed on YouTube, LinkedIn, and X 👉 RSVP: lu.ma/mlflow423 #opensource #mlflow #oss

I find that most of the (many, many) resources on MCP published in the past weeks don't provide small, self-contained examples build on. I tried to do that here. Here's a post on making an MCP server with one tool and using it with Claude desktop. www.danliden.com/posts/202504...