Where in the world is Claire? 🌵 ☀️ Working for a remote first tech company is amazing! Last week I was in Scottsdale and Sedona Arizona spending quality time with family, and working away on my latest research project on LLM evals. #remotejob #womeninscience (We're hiring!)

⭐⭐⭐New speakers announced for the 6th Annual @MLOpsWorld Summit (Oct 8-9, Austin). New sessions added from @pagerduty, @BlackRock, @Cometml, @patternhq, & @usebraintrust tackle testing, evals, and scaling. Early Bird ends Sept 8, 11:59PM ET → https://t.co/z7LKmyDtb4

I am hosting Las Vegas Hack Night. Join me! https://t.co/2dyFkYgOp9 via @LumaHQ

In Paris 🇫🇷 for #GTCParis and #VivaTech2025 and this place is an endless sea of AI companies, tech infrastructure and everything in between.

Build your first AI agent + MCP Server in Python. Here is everything you need to build your first AI agent in less than 20 minutes. About the code you'll see here: 1. I used Google ADK with Gemini Flash to power the agent 2. The agent connects to an MCP server 3. It also

Advanced Hybrid RAG with miniCOIL, LangGraph, and @deepseek_ai 🚀 @TRJ_0751 shows how to build a hybrid Customer Support RAG chatbot using miniCOIL to augment sparse retrieval with semantic awareness ➡️ LangGraph by @LangChainAI orchestrates the hybrid flow with MMR and

I've been thinking a lot about Agent evals... while LLM as a Judge works great for text, how are y'all approaching evaluation metrics for voice, image and/or video? 🤔

That’s a wrap on #AWSSummit London! 🚀 Next stop: Amsterdam 🇳🇱 for an @AITinkerers on May 6th. Still time to snag a spot 👉 https://t.co/S9uWodBgmt

⭐️⭐️ Lecture 9 of @MITDeepLearning 2025 is now available online #FREE for ALL! Should there be a Hippocratic Oath for #AI? Tune in to hear about this from the amazing @DougBlank3 of @Cometml! 🚀 🔥 Lecture 👉 https://t.co/2afd3SS2tB 🌐 Website 👉 https://t.co/sJuzYhGdY5

Reinforcement Learning (RL) is quickly becoming the most important skill for AI researchers. Here are the best resources for learning RL for LLMs… TL;DR: RL is more important now than it has ever been, but (probably due to its complexity) there aren’t a ton of great resources

👨‍💻 How do we improve AI Agent transparency and reliability? @StatInStilettos will dive into AI Agent observability, sharing how logging traces and monitoring help track Agent behavior and detect failures! 👉 April 15, 2025 | Register here: https://t.co/VkkLtA75oi

Now, I'm working with Opik, Comet's open-source library for LLM Observability. If you want to build your resume by contributing to OSS, I can help you! Opik is a great place to start. on the issues page, you will find some low-hanging fruit. https://t.co/1fysZ773lf

Creating and contributing to open-source projects helped me; 🔷 Build a developer portfolio to showcase my code 🔷 Be prepared for coding interviews 🔷 Connect with people who served as professional references

6 years ago, I decided to open-source my Python code for a personal project I was working on, which led to numerous career successes that followed. Not just for myself but for some of the folks I met and collaborated with. Anyone else have a similar experience?

Let's compare Llama 4 and DeepSeek-R1 using RAG:

I'm convinced we are living in a simulation. Here is some more evidence - look how easy it is to build one 🤯 ! https://t.co/UbqcdlPJIF

I just built a Multi-Agent AI system in under 2 hours. 🛠️ If you want to build your own Agents with Observability, check out the easy to use integration with CrewAI and Opik https://t.co/60Jc6zxX6c. I was able to copy-paste this examplee to get my own code from 0 to hero!

@AITinkerers link to register

Ollie and I are headed to Las Vegas for @AITinkerers May8th! If you're an AI developer and looking for a group of technical folks to network with, this is your crew! We'll be kicking off the first event with some fun technical demos. Hope to see you there! #AI #LasVegas

I love seeing Reinforcement Learning surging in popularity these days. With interesting crossovers with psychology and new applications in GenAI, RL is by far the most powerful mathematical framework in my mind.

There is a new benchmark dataset on Huggingface - pokerbench! Of course I'm all over this. https://t.co/dO9LhOmOue ♦️ ♣️ ♥️ ♠️