Sameer Tiwari

We are excited with the progress in AI and its potential to positively impact our world. It's crucial that we advance AI responsibly. I'm proud of our team for their exceptional work in this area! As the saying goes, 'you can't improve something that can't be measured'. To measure for unfair bias in any system, for example by race or gender, one would need to know the attributes. However, with the knowledge of those attributes, one would worry about unintended consequences. This blog post describes how we addressed the issue by developing methods for measurement while preserving privacy. https://lnkd.in/gqDtPR8U

96

7 Comments

Large Language Models (#LLMs) are evolving rapidly, and the demand for running them at scale is skyrocketing. #Ollama is stepping up to meet this need with its official container image on Docker Hub, excelling in local #deployments. However, there’s a catch for containerized environments: downloading #models requires the ollama serve command to be running within the #container. This extra step complicates automated deployments via #CI #CD #pipelines, making seamless model access challenging. To take your #model to production, it needs to be #container-ready—a feature Ollama has yet to fully support. The gap in #AIOps for smooth deployments gets blurred with the inference services available as an easy way to take it to production. Goal is to overcome obstacles and deliver solutions 😉 so here is to get you started on having your (O)#llama #production ready in a private #deployment from your #local to #cloud all in #oneshot . Enjoy Medium: https://lnkd.in/g9jqBQ8d dev.to: https://lnkd.in/gi_gGwam #AI #LLM #Ollama #llama3 #phi3 #mistral #S6overlay #AIOps #CI #CD #oneshot #container #docker #podmanEnjoy

11

Very useful insights for folks who are starting to dig further and further into the realm of LLM. An easier GUI approach for fine tuning LLMs.

9

Google Cloud and Anthropic made some exciting announcements: 📣 Claude 3 Opus, Anthropic’s most intelligent model, is now generally available on Vertex AI ⚙️ Tool use is available for the Claude 3 model family on Vertex AI, enabling Claude to act as an autonomous agent 📈Provisioned throughput is available for the Claude 3 model family on Vertex AI

3

Use Flux and SpinKube together! Check out this latest blog post based on the conversation Sohan Maheshwar had with Flux expert Kingdon Barrett https://lnkd.in/gbGwsddq #spin #wasm #flux #cicd

10

Happy to be speaking at Arize:Observe 2024 about GenAI Evaluation with a few wonderful colleagues from Google Cloud. 📅 For GenAI apps, answering the question of "How to measure success?" is non-trivial yet key to iterative improvement. If you are a developer, come talk to me. We would love to brainstorm, learn your thoughts and unique approach towards GenAI model and application evaluation. 🧑‍💻 Arize AI #GenAIEvaluation

86

9 Comments

Please join me on June 25th San Francisco, CA, USA for a panel titled "A BLUEPRINT FOR SCALABLE & RELIABLE ENTERPRISE AI/ML SYSTEMS" w/ moderation by Hira Dangol from Bank of America and my fellow panelists Rama Akkiraju from Nvidia and Nitin Aggarwal from Google. Recent breakthroughs in AI technology have captured the world's attention, and now it's time to address the challenge of creating truly robust and reliable AI systems. AIQCon's mission is to harness the power of our community to develop new GOLD STANDARDS for AI quality. The global movement is bringing together renowned leaders and professionals from across the industry to establish reliable AI quality solutions and standards. If you're working on AI systems, you won't want to miss this one! Use the discount code "Community" for a 15% discount on registration. Register at https://lnkd.in/gqRE48fC. #AI #EnterpriseAI #AIQuality #AIQCon https://lnkd.in/gqRE48fC

58

3 Comments

The Site Reliability Engineering: How Google Runs Production System book is arguably one of the most prevalent and well-known SRE resources out there, but there are many other great options for folks looking to expand on their learning. We recently spoke to Google's Reliability Advocate, Steve McGhee, in our Humans of Reliability interview series. In addition to his interesting anecdotes on the early days of SRE at Google, and his journey to becoming a Reliability Advocate, he also shared a handful of his favorite SRE resources, which we compiled here into a list: https://lnkd.in/gpUVhyRa

16

Massive news for AI enthusiasts (and anyone looking to give their business a serious edge)! Did you hear about Google's new Tensor Processing Unit (TPU) v6, codenamed Trillium? This is a game-changer for AI processing power. Ready to supercharge your AI efforts? ⚡️ Reach out to the team CloudWerx today, and let's chat about how TPUs can revolutionize your business!

20

Meet #ConfluentCatalyst Vinod Chelladurai! Vinod shared with us how he first got involved in the Apache Kafka/Apache Flink community, what he enjoys most about being a part of the community, his favorite project, and more! Check out his story below and learn more about our Community Catalysts of the week here → https://cnfl.io/3vV53uC

49

2 Comments

Need accuracy & speed in your GenAI stack? Superlinked + Redis = smarter and faster apps. Tyler Hutcherson Ben Gutkovich Daniel Svonava Ash Vijayakanthan Jim Allen Wallace Albin Bergh Yael Fainsilber Adrienne Cohen #RAG #genai #vectordb

20

3 Comments

We're thrilled to feature "μOpt: An Efficient Optimal Autoscaler for Microservice Applications," recipient of the Best Paper Award at ACSOS 2023, in our ongoing Paper Spotlight series. This paper introduces μOpt, an efficient model-based autoscaler for cloud-based microservice architectures. By solving a nonlinear optimization problem that embeds a layered queueing network (LQN) model, µOpt proactively computes optimal configurations maximizing performance while minimizing allocated resources. More in detail, µOpt works like this: * At design time, the user defines an LQN model of the application, µOpt automatically generates its fluid representation and the relative non-linear optimization problem formulation. * At runtime, µOpt operates following the time-triggered MPC philosophy. It solves the optimization problem, thus computing the optimal configuration given the measured current number of users, the target KPI, and the constraints of the system. It then proceeds to apply the optimal configuration with vertical and horizontal scaling actions. Comparative analysis in the study demonstrates that μOpt outperforms a state-of-the-art autoscaler, achieving approximately 6% to 8% higher performance, using about 15% to 35% fewer resources, and reporting fast solution times (∼0.1 s) which is significant in scenarios involving highly variable workloads. For a more comprehensive understanding of μOpt check out the full paper. https://lnkd.in/d2ezs8RA Emilio Incerto Roberto Pizziol Mirco Tribastone Scuola IMT Alti Studi Lucca #ACSOS #IEEE #Research

15

pgvectorscale: A Game-Changer for Vector Similarity Search 🚀 Timescale's #pgvectorscale extension for PostgreSQL has achieved a remarkable milestone, matching the performance of Pinecone, a dedicated vector database, while being 75% more cost-effective. 💰 In their latest blog post, Timescale showcases the impressive speed and efficiency of pgvectorscale, which leverages the power of PostgreSQL to deliver lightning-fast vector similarity search. This breakthrough opens up new possibilities for applications like semantic search, recommendation systems, and more. 🔍 Key takeaways: 🌟 pgvectorscale now matches Pinecone's performance in vector similarity search 💸 pgvectorscale is 75% more cost-effective compared to Pinecone 🔧 Easy integration with existing PostgreSQL databases 🌐 Scalable solution for handling billions of vectors ⚡ Optimized for fast and efficient search results pgvectorscale's seamless integration with PostgreSQL allows developers to incorporate vector similarity search into their applications with ease, while benefiting from the robustness and scalability of a proven database system. 🗄️ If you're looking for a high-performance, cost-effective solution for vector similarity search, pgvectorscale is definitely worth exploring. 🔍💡 #pgvectorscale #postgresql #vectorsimilaritysearch #semanticsearch #recommendationsystems #timescale https://lnkd.in/gsfgCK32

5

So much fun talking about the power of LLMs with Amazon Bedrock and Anthropic Claude. In summary, the ever-evolving landscape of GenAI, it's becoming clear that there won't be a single LLM (Large Language Model) to rule them all. The rise of application-specific LLMs heralds a new era, where various models will carve out niches to excel in. This diversity opens up a wide playing field for innovation and tailored solutions. When it comes to deploying AI models, striking the right balance in evaluation is paramount. We must weigh factors like cost, speed, and precision to ensure optimal performance and resource utilization. Finding this equilibrium ensures that our GenAI solutions are not just efficient but also effective in real-world scenarios. Anthropic Claude emerges as a frontrunner in the realm of LLMs, distinguished by its exceptional capabilities and groundbreaking advancements. Boasting unparalleled scale, efficiency, and adaptability, Anthropic Claude represents a pinnacle of GenAI innovation. Its ability to seamlessly integrate with Amazon Bedrock amplifies its prowess, providing users with an unparalleled ecosystem for knowledge integration and generation. With state-of-the-art architecture and a commitment to pushing the boundaries of what's possible, Anthropic Claude stands as a testament to the transformative potential of GenAI in shaping the future of technology and beyond. Prompt engineering holds the key to maximizing the potential of applications. Crafting prompts that consider persona, context, tags, and positioning can significantly enhance the model's ability to comprehend and generate relevant responses. This strategic approach empowers AI systems to better serve their intended purposes. In the realm of GenAI architectures, a robust knowledge base is essential. Amazon Bedrock stands out as a key component for architectures like RAG (Retrieval-Augmented Generation), providing a solid foundation to fuel intelligent decision-making and content generation. As we march towards AI integration, bridging the gap with legacy applications is crucial. Agents equipped with open APIs offer a seamless way to facilitate communication and interoperability, ensuring a smooth transition into the AI-driven future. Let's continue to explore, innovate, and collaborate as we navigate the exciting frontier of GenAI together! #aws #LanguageModels #Innovation #TechTrends #AIIntegration #webdevcon #claude #bedrock

68

Thanks, Swapnil Bhartiya, for precisely outlining the current state of AI for enterprises and potential challenges and for your thought-provoking questions.

22

1 Comment

Hallucinations in LLMs are inevitable, no seriously! Josh Fritzsche and I have worked hard at Voze to find a way to tune, prompt and even plead 🙏 with LLMs to prevent them from the occasional 🍄 hallucination. It seemed like the better we have done the harder the edge cases have been to solve and eventually we realized that they tend to frequently happen when LLMs predict or make anticipations on "nothing". I remember at one point nearly going insane with frustration because when LLMs had a hallucination, they were EPIC! 😱 Then we pushed through it and benefited for the effort! How did we solve this common problem? We didn't (Not completely), we got better at identifying the issues as they happened. Once we identified in the data we were able to start looking for patterns. The same catalysts that cause it to happen once if left unchanged caused it over and over again. Our solution is astoundingly simple. Once you know that it's likely to happen..... let it! Accept it will 🍄, but also be preemptive in not focusing on it and use alternative data sources, generators or providers. Change the conditions that cause it but continue to monitor it as it happens. As Dan Caffee is fond of saying to me on a regular bases. "Dusty we need the system to be adaptive and provide mechanisms to learn from it's past." Well he is right! All we needed was data and the people that contribute to it's quality. Huge props 👏 to strong support from Kathy and Janelles audit teams. We were armed with a knowledge and a desire to learn from past mistakes. Armed with confidence that we could correct these problems we could focus on the data to prevent their impact going forward. When doing millions of LLM (Generative AI) calls regularly Josh and I have learned that hallucinations will happen. We also know exactly how we will handle and prevent it going forward! Failure is not doing anything and accepting defeat.

4

2 Comments

This insightful blog post by Manpreet(Manny) Sidhu explores how to leverage this low-power, long-range network with AWS IoT Core to build track and trace applications. Perfect for various asset tracking usecases!.

2