Kai Du

Thats the exact explanation I gave to a group of investors last week. (… it’s just Precision/Recall, attributes vectorization as “embedding”, K-Nearest Neighbor, User Search Intent, DAG, ML algorithms, etc all over again …). LOL and they asked what’s new this time around. And I was like not much, ML is still the backbone, and AI is the inference and actions based on the model. It works better when there is a feedback loop in a closed system. But the current state of the art like ChatGPT is based on scraping the Internet (garbage in, garbage out). Kinda like early search engines. What is a better analogy is that NVIDIA/Snowflake etc are selling tools, aka pickaxes to prospectors. The gold is up to you to find. And the opportunity right now is to monetize industry specific (healthcare, travel, financial services) clean data to build models with (aka a treasure map for the prospectors). From an enterprise perspective, what’s out there today aka generative AI isn’t very useful. Too much hype. To build useful engines will require an effort similar to search revolution 2 decades ago. From

14

3 Comments

There is so much research going into bringing the power of LLMs into the Enterprise context. The main techniques are k-shot learning or prompt engineering, RAG (Retrieval Augmented Generation) & Model Fine tuning (not to mention many variations of these e.g. Agentic RAG, GraphRAG etc.) However, I came across an interesting take on this from IBM and they are calling it "InstructLab" - where the claim is that they are able to teach the LLM "new skills" grounded in an Enterprise context. On the surface it looks like a k-shot learning + fine turning on steroids. Approach seems to be to utilize a small "skills training dataset" in order to generate a large synthetic dataset (perhaps utilizing a specialized LLM) that is then incorporated into the LLM weights natively. This could be a very interesting concept as long as the cost of adding new skills is not very high (when compared to fine tuning). Exciting times! #genAI #enterpriseAI

40

2 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

Great article by Roi Yarden Building Data pipelines comes with its set of challenges. One of the most important decisions is to understand what patterns suit the business evolving needs and allow for a system to scale. This can prevent very costly mistakes.

8

Truth. This blog articulates the shortcomings of most tiered storage solutions in delivering predictable performance at scale. Without some rebuild that harnesses cloud primitives like AWS S3 and GCP GCS, mere incremental adjustments to existing products won't adequately serve users. From a product manager's perspective, sometimes incremental adjustments isn't a path to sustainable product adoption and success.

9

Excited to announce our upcoming webinar! 🚀 I have seen the challenges of managing complex ML pipelines so many times. Join us on May 29th at 11:30 AM EDT to learn why using too many tools can hinder your project's success and how to avoid these traps. Don't miss out! Register here: https://lnkd.in/dt3F29iV #MachineLearning #DataScience #QwakAcademy #MLPipeline #TechTalk #MLOps

8

Seismic’s AI enablement assistant, Aura Copilot, is now available for early access. Teams can now get faster access to answers and content, automate tedious tasks, and gain insights for better business decisions. Aura also now integrates with Microsoft Teams and Microsoft 365 Copilot to give teams in-the-moment answers and content recommendation. https://lnkd.in/d_mSbDXK

44

1 Comment

A very insightful and practical report from LinkedIn team thanks to contributions from Juan Pablo Bottaro and Karthik Ramgopal. Some interesting points about using YAML instead of JSON for structured output training. In addition, interesting to note that training was primarily implemented through prompt engineering. #generativeai #responsibleai

7

Stand on the platform or jump onto the fast-moving train? Jensen Huang, founder and CEO of Nvidia, advocates for immediate action to keep up with rapidly growing trends. Take a page from Huang's playbook and don't just observe, act. Be the engine, not just a passenger. Intrigued? Learn more here: https://lnkd.in/eRKZbpvp What are you doing to drive change and #transformation ?? #databricks #nvidia #genai #generativeai

5

How do the costs compare of implementing a low-latency write-ahead-log (WAL) on S3 Express One Zone and one implemented as a State-Machine-Replication (SMR) system (such as Paxos/Raft/Kafka)? I built a cost model for both to find out. https://lnkd.in/dwczVutW

43

5 Comments

*Mixture of Agents (MoA)* is an innovative way to boost Large Language Models’ performance by leveraging the strengths of multiple agents as a team. Layered Architecture: MoA arranges many LLMs in layered architecture, each layer composed of numerous individual agents(LLMs). Collaboration: These agents generate responses that are based on outputs from the previous layer’s agents. They repeatedly refine and enhance the last output. Diverse Insights: By integrating different capabilities and insights from various models, MoA achieves a more powerful combined model that is secure against diverse risks. Performance Boost: MoA outperforms standalone LLMs by a wide margin. For instance, it set a new benchmark with 65.1% on AlpacaEval 2.0 as against GPT-4 Omni at 57.5%, using only open-source models. In short, if we combine language modelers’ strengths then it results in increased efficiency and versatility. Here is a nice implementation of MOA by Together AI Github source: https://lnkd.in/dMCVRS3D #AI #LLM #LargeLanguageModels #MachineLearning

59

3 Comments

Here's the technical breakdown of the AI Penalty Challenge authored by Alok Pattani (check out this video if you haven't seen the demo yet: https://lnkd.in/gsD3xjJ2) Key Takeaways: ☁️ Firestore for triggering slow-mo video capture on Android phones & uploading to Google Cloud via Firebase Storage. 🧠 Cloud AutoML for training custom object detectors (ball & goal tracking) to calculate speed & accuracy. 🗣️ Gemini Pro 1.5 on Vertex AI for personalized coaching feedback based on multiple data points. 🎨 Imagen on Vertex AI for instant, prompt-driven image editing for cool player pics. More technical insights from the project to come... #AIChallenge #MachineLearning #SportsTech #GoogleCloud #footballNOTsoccer

89

6 Comments

Data ablations are the lifeblood of any LLM training process and are key to LLM performance in practice. At Snowflake, we believe know-your-data is a key part of the promise we'll make to training LLMs. So for the curious among you, here's the third blog in our Snowflake Arctic cookbook series. This one's on data, and peers behind the curtain on our data recipe for Arctic.

92

3 Comments

One of the key capabilities that sets Memgraph apart from the competition is our deep path traversal algorithms. Come read our latest blog explaining all about it: https://lnkd.in/gBtWPJuZ

27

2 Comments

A super clear, straight forward example of how to do cost effective RAG using LangChain for your document pipeline and Groq for compute resources. The code demonstrates how to speed up RAG and reduce costs using quantized embeddings (reducing 32 bit values to 8) Nice job Sahibpreet Singh! https://lnkd.in/gf5QMCKK

44

2 Comments

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

Signal boosting this post from my colleague Arun Shankar. My snarky summary "It's like caching, but semantic" :P Oddly, I think it's a reasonable summary... semantically similar inputs hit the same cache, otherwise dissimilar input miss.... ... but how do you do that on non-exact matches and how to you manage such a system? I guess you'll have to read: https://lnkd.in/gPgtM8T5

13

1 Comment