Jennie Lindahl’s Post

"Excited to share a comprehensive guide on harnessing the power of Amazon Bedrock for AI development! walk through gaining model access, connecting AWS to Visual Studio Code, utilizing the Titan Image Generation API, and developing a complete image editing app with Streamlit. Learn how to overcome common challenges like resolving Axios errors and image length issues. Whether you're a seasoned developer or just starting out, this tutorial will equip you with the skills to create transformative AI applications." #generativeai #artificialintelligence #amazonbedrock complete tutorial link: https://lnkd.in/dsEPxRcD github: https://lnkd.in/dD-WqYQc

GitHub Copilot Chat now uses GPT-4o! 🤖 Copilot Chat leverages OpenAI's latest model for faster response times (up to 55% faster TTFT) and more accurate suggestions. https://buff.ly/4cdqPJ4

Introducing the LangChain Firestore Vector Store Integration 🚀 📑 You can now turn your documents into vectors, index them in Firestore, and query them easily using LangChain! Add, update, or search vectors in Firestore with just a few lines of code. ✨ Build generative AI apps with Firestore using the new integrations, which combine well with other LangChain components. 🔗 Usage demo: https://lnkd.in/eVPTVtif

Today, I earned my "Responsible AI with GitHub Copilot" badge as part of the comprehensive GitHub Copilot Fundamentals course! This course is all about leveraging the power of AI in coding responsibly, and Up next, I’m focused on completing the entire course to dive deeper into AI-assisted development and pair programming with GitHub Copilot. #AIDevelopment #ResponsibleAI #GitHubCopilot

Hugging Face recented released an open-source LLM observability library called **Observers** Observability is crucial when building or serving LLM apps (especially agentic LLM apps) and **Observers** can be easily integrated to any app powered by the OpenAI client. I'm looking forward to what features will be added to the later versions! Related blog: https://lnkd.in/gba9jmDQ

GitHub Copilot is a coding assistant powered by Artificial Intelligence (AI), which can run in various environments and help you be more efficient in your daily coding tasks. In this new video, Bruno Capuano shares best practices like interfacing via natural language to better harness Copilot. https://lnkd.in/gAaTTuuX #GitHub #Copilot #AI #msftadvocate

I'm delighted to share that we have launched ExecuTorch for its Alpha release as the PyTorch ecosystem solution for mobile and edge deployments. Since the successful preview at last year's PyTorch Conference, we've added many major improvements in terms of capabilities, performance, and model scope. A particular emphasis for this release was support for Large Language Models -- with this version of Executorch, you can deploy LLMs to mobile and edge devices, including iOS, Android, and more. This is also the culmination of so many partnerships with hardware vendors and software partners that enable a broad set of devices and several hardware-optimized backends ("delegates"). A big shout-out to the entire Executorch team, who have brought PyTorch and PyTorch-powered LLMs for self-service deployment to mobile and edge platforms working with the global PyTorch team and building on the same compiler technology that powers PT2 compilation. Check out a video of llama2 running on a phone with Executorch https://lnkd.in/gzXpebXH. Executorch comes with instructions and sample applications for iOS and Android mobile applications that may be used to chat with LLMs, and support the newly released Llama3, and the popular Llama2 family as well as many other models. You can read more about Executorch at our blog at https://lnkd.in/guyXCb4i, check out the Executorch repo at https://lnkd.in/g9uVqKgR or install Executorch wheel with pip install with Python 3.10. So download Executorch and try to run the most exciting models on your phone, tablet and more. If you are a maker that's excited about the possibilities of devices such as Raspberry Pi, deploy LLMs on these devices with either Raspbian or Android. Then share on what devices and how you are using Executorch! #ExecuTorch #PyTorch #LLM #MobileLLM #AcceleratedAI

#GitHub #Copilot #Chat and pull request summaries are now powered by #GPT-4o🥂 1️⃣ Available in Visual Studio, VS Code, JetBrains IDEs, GitHub Mobile apps, and GitHub.com 2️⃣ Faster response times – up to 55% faster TTFT (time to first byte) and 🆕 return code that could match publicly available code on GitHub.com! 3️⃣ 60% increase with accurate and reliable Copilot Chat responses‼️ Learn more 👉https://lnkd.in/d9fvxrRq

#BlackHat Webinars present "Live Hack: Exploiting AI-Generated Code with Snyk" on February 27. In the span of one hour, we’ll build a demo app using GitHub Copilot and ChatGPT, and live hack the results, showing how the generated code can be exploited >> https://lnkd.in/eKTr4a9q

I found out that my 15 public GitHub repos are part of a public dataset for coding AI. Uh-oh, I didn't consent to that BigCode GitHub Hugging Face ! "The Stack" dataset has scraped the internet for gobs of public code. I had little idea that my code was taken for AI training without anyone asking me. Is this the new internet norm, where anything you put online can be taken for AI training without your consent/permission? Developers of The Stack say they take anything without an explicit license. They have little idea about the automatic registration of copyright that everyone gets on their code/literary works when the works are produced (this is the case in the Indian Copyright Act). #ai #future #coding #copyright https://lnkd.in/gxuR_EQ2