Marcel de Vries’ Post

Wow, what an incredible experience it has been! 🙌 Huge shout out to CodePath for an amazing EES 2024! It is Day 3 of EES 2024, and things are closing out strong. 💪 Special thanks to Tim Lee and Vivek Ravisankar for dropping invaluable insights on how to leverage AI to become a better developer. Here's a standout qoute from the session that really resonated with me: "If you're not meeting your expectations with your goals, you need to change the way you're approaching them." Powerful advice to staying flexible and adjusting as we go on our journey! 🚀 #EES2024 #CodePath #AI

A new minion in my stack - Fabric I've added Fabric - an opensource project by daniel messler - to my AI toolkit, and it's really intriguing. It is certainly not mainstream and somehow doubt that it goes that way, but its open-source framework offers a unique and forward-thinking approach to handling AI tasks. The crowd maintained patterns - aka promps and its ability to pipe specific tasks together, connecting to different models is as "agentic" as I see reliable solutions right now - without the independence though. But lets wait. #AI #OpenSource #Innovation #TechTools

Tired of constantly fine-tuning LLM models, dealing with time-consuming processes, and using up valuable storage space? Try Retrieval-Augmented Generation (RAG) in LangChain! Discover how this innovative approach can revolutionize your AI and ML projects. Swipe through to learn more! 👇 ✨ Start you RAG journey now: https://lnkd.in/edA2cGj2

🚀 Just wrapped up the "Introduction to Generative AI - Art of the Possible" course from AWS! Excited to share the first set of key takeaways, focusing on innovative Gen AI use cases. Stay tuned for more insights! 💡 #GenerativeAI #AIInnovation #AWSLearning #TechTrends #AIUseCases #ContinuousLearning #FutureTech #AIRevolution Feel free to adjust any details or add any personal touch!

I am often in discussions with organizations about all aspects of LLMs, with one of the most common questions being which model to use. Choosing a model is a very small step in an AI use case. The real question is: once you do your initial trials, what's next? Scaling an LLM model #llmops has fundamentally the same considerations and challenges as scaling predictive ML models #mlops. You still need to evaluate your model with some metrics, iterate quickly on the various steps and reproduce them, observe the various steps of the pipeline, and monitor user feedback to ensure the output serves its purpose. I really enjoyed watching this video from Hien Luu , presented during #Databricks summit, where he shares the foundational aspects of experimenting and scaling your LLM usecases for long run. Watch it here -

Soar to new #AI heights with Anthropic’s upgraded Claude 3.5 Sonnet model, now available in #AmazonBedrock! 🚀 https://go.aws/4ebcoGm With the upgraded Claude 3.5 Sonnet, #AWSPartners can use AI to innovate even more for customers. Claude 3.5 Sonnet’s latest advancements include: 📊 Wide-ranging improvements on industry benchmarks 🤖 Significant coding improvements 💻 New computer use capability to perceive & interact with computer interfaces #generativeAI #Anthropic

The most important talks in AI are happening at AI_dev: Open Source GenAI & ML Summit Europe! Check out "Code Security Reinvented: Navigating the Era of AI" with Joseph Katsioloudes of GitHub & register to join us in Paris from 19-20 June. Reserve your spot by 2 June & save US$150! https://hubs.la/Q02vzLHK0 #AIDev #GenAI #GenerativeAI #ML #AI #MachineLearning #OpenSource #OSS #GenAI #LinuxFoundation #events #OpenSourceDevelopment #OpenSourceCommunity #OpenSourceSoftware

This is another good introduction to Generative AI from Databricks. It covers basic concepts of GenAI and LLM, followed by more advanced GenAI Engineering, where you can learn how to build LLM apps using Hugging Face and RAG, create multi-stage reasoning pipelines using LangChain, fine-tune LLMs for specific tasks, assess and address societal considerations of using LLMs, and learn how to deploy your models at scale leveraging LLMOps best practices. You can access it here: https://lnkd.in/gj2_Bneb #generativeai #llm #llmops #databricks

🌐✨ You are code! But unlike tech code, your time is limited! Check this article: https://lnkd.in/dh9mTs3w Have you noticed how AI tech is striving to reproduce the way our brain works? Our minds are the ultimate source code—wired, programmed, and ready to shape the narrative of our existence. 💡 Just like AI, our thoughts (that we can sure turn into beliefs) are the commands steering our actions. We impact ourselves and the world, leaving a legacy defined by the code we live by. ⏳ While AI algorithms seem to go for an everlasting existence, yours is coming to an end (and quite soon compared to AI), our time is limited. The culmination of your code is your death. And all that will be left of your code is the impact it had on the world, in your day-to-day actions—a reminder that our actions echo beyond the present. 🚀 So, code wisely! Adjust your beliefs, fine-tune your actions, and align your day-to-day actions with that vision of the world you deeply wish for. You are the author of your code, the architect of your legacy. Own it and be honest with yourself! 💚🔥 #YouAreCode #CodeKO_DEP #LifeBasedCareer