AI Distilled 33: Tech Revolution 2024: AI's Impact Across Industries

Dive deeper into the world of AI innovation and stay ahead of the AI curve! Subscribe to our AI_Distilled newsletter for the latest insights. Don't miss out – sign up today!

👋 Hello ,

“This year, every industry will become a technology industry. You can now recognize and learn the language of almost anything with structure, and you can translate it to anything with structure — so text-protein, protein-text. This is the generative AI revolution.” -Jensen Huang, NVIDIA founder and CEO. 

AI is revolutionizing drug development and reshaping medical tech with cutting-edge algorithms. Dive into the latest AI_Distilled edition for sharp insights on AI's impact across industries, including breakthroughs in machine learning, NLP, and more. 

AI Launches & Industry Updates:  

OpenAI Revises Policy, Opening Doors to Military Applications 

Google Cloud Introduces Advanced Generative AI Tools for Retail Enhancement 

Google Confirms Significant Layoffs Across Core Teams 

OpenAI Launches ChatGPT Team for Collaborative Workspaces 

Microsoft Launches Copilot Pro Plan and Expands Business Availability 

Vodafone and Microsoft Forge 10-Year Partnership for Digital Transformation 

AI in Healthcare:  

MIT Researchers Harness AI to Uncover New Antibiotic Candidates 

Google Research Unveils AMIE: AI System for Diagnostic Medical Conversations 

NVIDIA CEO Foresees Tech Transformation Across All Industries in 2024 

AI in Finance: 

AI Reshapes Financial Industry: 2024 Trends Unveiled in Survey 

JPMorgan Seeks AI Strategist to Monitor London Startups 

AI in Fintech Market to Surpass $222.49 Billion by 2030 

AI in Business: 

AI to Impact 40% Jobs Globally, Balanced Policies Needed, Says IMF 

Deloitte's Quarterly Survey Reveals Business Leaders' Concerns About Gen AI's Societal Impact and Talent Shortage 

AI in Science & Technology:  

NASA Boosts Scientific Discovery with Generative AI-Powered Search 

Swarovski Unveils World's First AI Binoculars 

AI in Supply Chain Management: 

AI Proves Crucial in Securing Healthcare Supply Chains: Economist Impact Study 

Unlocking Supply Chain Potential: Generative AI Transforms Operations 

We’ve also got you your fresh dose of LLM, GPT, and Gen AI secret knowledge and tutorials: 

How to Craft Effective AI Prompts 

Understanding and Managing KV Caching for LLM Inference 

Understanding and Enhancing Chain-of-Thought (CoT) Reasoning with Graphs 

Unlocking the Power of Hybrid Deep Neural Networks 

We know how much you love hands-on tips and strategies from the community, so here they are: 

Building a Local Chatbot with Next.js, Llama.cpp, and ModelFusion 

How to Build an Anomaly Detector with OpenAI 

Building Multilingual Financial Search Applications with Cohere Embedding Models in Amazon Bedrock 

Maximizing GPU Utilization with AWS ParallelCluster and EC2 Capacity Blocks 

Don’t forget to review these GitHib repositories that have been doing rounds:  

vanna-ai/vanna 

dvmazur/mixtral-offloading 

pootiet/explain-then-translate 

genezc/minima 

📥 Feedback on the Weekly Edition

Take our weekly survey and get a free PDF copy of our best-selling book, "Interactive Data Visualization with Python - Second Edition." 

We appreciate your input and hope you enjoy the book! 

Writer’s Credit: Special shout-out to Vidhu Jain for their valuable contribution to this week’s newsletter content!  

Cheers,  

Merlyn Shelley  

Editor-in-Chief, Packt 

SignUp | Advertise | Archives

⚡ TechWave: AI/GPT News & Analysis

AI Launches & Industry Updates: 

💎 OpenAI Revises Policy, Opening Doors to Military Applications: OpenAI updated its policy, lifting the ban on using its tech for military purposes, aiming for clarity and national security discussions. However, it maintains a strict prohibition against developing and using weapons. 

💎 Google Cloud Introduces Advanced Generative AI Tools for Retail Enhancement: Google Cloud has released new AI tools to improve online shopping and help retail businesses. This includes a smart chatbot for websites and apps to help customers, a feature to make product searches better, and tools to improve customer service and speed up listing products. 

💎 Google Confirms Significant Layoffs Across Core Teams: Google announced major job cuts affecting its Hardware, core engineering, and Google Assistant teams, totaling around a thousand layoffs in a day. The exact number might be higher, but no total count was provided. 

💎 OpenAI Launches ChatGPT Team for Collaborative Workspaces: ChatGPT Team is a plan for teams offering a secure space with advanced models like GPT-4 and DALL·E 3. It includes tools for data analysis and lets users create custom GPTs, ensuring business data remains private. 

💎 Microsoft Launches Copilot Pro Plan and Expands Business Availability: Copilot Pro, at $20/month per user, offers enhanced text, command, and image features in Microsoft 365 apps, plus early access to new GenAI models. It's also available for businesses on various Microsoft 365 and Office 365 plans. 

💎 Vodafone and Microsoft Forge 10-Year Partnership for Digital Transformation: Vodafone and Microsoft have formed a 10-year partnership to serve over 300 million people in Europe and Africa, using Microsoft's AI to improve customer experiences, IoT, digital services for small businesses, and global data center strategies. 

AI in Healthcare: 

💎 MIT Researchers Harness AI to Uncover New Antibiotic Candidates: MIT researchers have employed deep learning to identify a new class of antibiotic compounds capable of combating drug-resistant bacterium Methicillin-resistant Staphylococcus aureus (MRSA). Published in Nature, the study underscores researchers' ability to unveil the deep-learning model's criteria for antibiotic predictions, paving the way for enhanced drug design. 

💎 Google Research Unveils AMIE: AI System for Diagnostic Medical Conversations: Google Research introduces the Articulate Medical Intelligence Explorer (AMIE), an AI system tailored for diagnostic reasoning and conversations in the medical field. AMIE, based on LLMs, focuses on replicating the nuanced and skilled dialogues between clinicians and patients, addressing diagnostic challenges. The system employs a unique self-play simulated learning environment, refining its diagnostic capabilities across various medical conditions. 

💎 NVIDIA CEO Foresees Tech Transformation Across All Industries in 2024: Jensen Huang predicts a tech revolution in all industries by 2024, focusing on generative AI's impact. At a healthcare conference, he highlighted AI's role in language and translation, and NVIDIA's shift from aiding drug discovery to designing drugs with computers. 

AI in Finance: 

💎 AI Reshapes Financial Industry: 2024 Trends Unveiled in Survey: NVIDIA's survey reveals 91% of financial companies are adopting or planning to use AI. 55% are interested in generative AI and LLMs, mainly to enhance operations, risk, and marketing. 97% intend to increase AI investments for new uses and workflow optimization. 

💎 JPMorgan Seeks AI Strategist to Monitor London Startups: JPMorgan is hiring an 'AI Strategy Consultant' in London to identify and assess startups using Generative AI and LLMs, reporting to the Chief Data and Analytics Officer. This aligns with financial trends like HSBC's launch of Zing, a money transfer app. 

💎 AI in Fintech Market to Surpass $222.49 Billion by 2030: The AI in Fintech market, valued at $13.23 billion in 2022, is growing fast. It's improving financial services with data analytics and machine learning, enhancing decision-making and security. It's projected to reach $222.49 billion by 2030, growing at 42.3% annually. 

 AI in Business: 

💎 AI to Impact 40% Jobs Globally, Balanced Policies Needed, Says IMF: The IMF warns that AI affects 40% of global jobs, posing more risks and opportunities in advanced economies than emerging ones. It may increase income inequality, calling for social safety nets, retraining, and AI-focused policies to ensure inclusivity. 

💎 Deloitte's Quarterly Survey Reveals Business Leaders' Concerns About Gen AI's Societal Impact and Talent Shortage: Deloitte's new quarterly survey, based on input from 2,800 professionals globally, shows 79% are optimistic about gen AI's impact on their businesses in 3 years. However, over 50% fear it may centralize global economic power and worsen economic inequality. 

 AI in Science & Technology:  

💎 NASA Boosts Scientific Discovery with Generative AI-Powered Search: NASA introduces the Science Discovery Engine, powered by generative AI, simplifying access to its extensive data. Developed by the Open Source Science Initiative (OSSI) and Sinequa, it comprehends 9,000 scientific terms, offers contextual search, and enables natural language queries for 88,000 datasets and 715,000 documents from 128 sources. 

💎 Swarovski Unveils World's First AI Binoculars: Swarovski Optik and designer Marc Newson launch AX VISIO, the first AI binoculars. They merge analog optics with AI, instantly identifying 9,000+ species, boasting a camera-like design, and enabling quick photo and video capture through a neural processing unit. 

 AI in Supply Chain Management: 

💎 AI Proves Crucial in Securing Healthcare Supply Chains: Economist Impact Study: A study by Economist Impact, with DP World's support, finds 46% of healthcare firms use AI to predict supply chain issues. Amid geopolitical uncertainties, 39% use "friendshoring" for trade, and 23% optimize suppliers, showcasing industry adaptability. 

💎 Unlocking Supply Chain Potential: Generative AI Transforms Operations: About 40% of supply chains invest in Gen AI for knowledge management. It's widely adopted (62%) for sustainability tracking and helps with forecasting, production, risk management, manufacturing design, predictive maintenance, and logistics efficiency. 

🔮 Expert Insights from Packt Community 

Generative AI with LangChain - By Ben Auffarth 

How do GPT models work? 

Generative pre-training has been around for a while, employing methods such as Markov models or other techniques. However, language models such as BERT and GPT were made possible by the transformer deep neural network architecture (Vaswani and others, Attention Is All You Need, 2017), which has been a game-changer for NLP. Designed to avoid recursion to allow parallel computation, the Transformer architecture, in different variations, continues to push the boundaries of what’s possible within the field of NLP and generative AI. 

Transformers have pushed the envelope in NLP, especially in translation and language understanding. Neural Machine Translation (NMT) is a mainstream approach to machine translation that uses DL to capture long-range dependencies in a sentence. Models based on transformers outperformed previous approaches, such as using recurrent neural networks, particularly Long Short-Term Memory (LSTM) networks. 

The transformer model architecture has an encoder-decoder structure, where the encoder maps an input sequence to a sequence of hidden states, and the decoder maps the hidden states to an output sequence. The hidden state representations consider not only the inherent meaning of the words (their semantic value) but also their context in the sequence. 

The encoder is made up of identical layers, each with two sub-layers. The input embedding is passed through an attention mechanism, and the second sub-layer is a fully connected feed-forward network. Each sub-layer is followed by a residual connection and layer normalization. The output of each sub-layer is the sum of the input and the output of the sub-layer, which is then normalized. 

The architectural features that have contributed to the success of transformers are: 

Positional encoding: Since the transformer doesn’t process words sequentially but instead processes all words simultaneously, it lacks any notion of the order of words. To remedy this, information about the position of words in the sequence is injected into the model using positional encodings. These encodings are added to the input embeddings representing each word, thus allowing the model to consider the order of words in a sequence. 

Layer normalization: To stabilize the network’s learning, the transformer uses a technique called layer normalization. This technique normalizes the model’s inputs across the features dimension (instead of the batch dimension as in batch normalization), thus improving the overall speed and stability of learning. 

Multi-head attention: Instead of applying attention once, the transformer applies it multiple times in parallel – improving the model’s ability to focus on different types of information and thus capturing a richer combination of features. 

This is an excerpt from the book Generative AI with LangChain - By Ben Auffarth and published in Dec ‘23. To see what's inside the book, read the entire chapter here or try a 7-day free trial to access the full Packt digital library. To discover more, click the button below. 

🌟 Secret Knowledge: AI/LLM Resources

💎 How to Craft Effective AI Prompts: Embark on a journey to understand the intricacies of AI prompts and how they can revolutionize creative content generation. Delve into the workings of AI Prompts, powered by NLP algorithms, and uncover the steps involved in their implementation. 

💎 Understanding and Managing KV Caching for LLM Inference: Explore the intricacies of KV caching in the inference process of LLMs in this post. The KV cache, storing key and value tensors during token generation, poses challenges due to its linear growth with batch size and sequence length. The post delves into the memory constraints, presenting calculations for popular MHA models. 

💎 Understanding and Enhancing Chain-of-Thought (CoT) Reasoning with Graphs: Explore using graphs to advance Chain-of-Thought (CoT) prompting, boosting reasoning in GPT-4. CoT enables multi-step problem-solving, spanning math to puzzles, vital for enhancing language models. 

💎 Unlocking the Power of Hybrid Deep Neural Networks: This article explains Hybrid Deep Neural Networks (HDNNs), advanced ML models changing AI. It covers HDNN architecture, uses, benefits, and future trends, including how they combine various neural networks like CNNs, RNNs, and GANs. 

🔛 Masterclass: AI/LLM Tutorials

💎 Building a Local Chatbot with Next.js, Llama.cpp, and ModelFusion: Discover how to build a chatbot with Next.js, Llama.cpp, and ModelFusion. This tutorial covers setup, using Llama.cpp for LLM inference in C++, and creating a chatbot base with Next.js, TypeScript, ESLint, and Tailwind CSS. 

💎 How to Build an Anomaly Detector with OpenAI: Learn to build an anomaly detector for different data types, including text and numbers, that fits into your data pipeline. The guide starts with the importance of anomaly detection and OpenAI's LLM role, using OpenAI and BigQuery.  

💎 Building Multilingual Financial Search Applications with Cohere Embedding Models in Amazon Bedrock: Learn to use Cohere's multilingual model on Amazon Bedrock for advanced financial search tools. Unlike traditional keyword-based methods, Cohere uses machine learning for semantic searches in over 100 languages, improving document analysis and information retrieval. 

💎 Maximizing GPU Utilization with AWS ParallelCluster and EC2 Capacity Blocks: Discover how to tackle GPU shortages in machine learning with AWS ParallelCluster and EC2 Capacity Blocks. This guide outlines a three-step method: reserve Capacity Block, configure your cluster, and run jobs effectively, including GPU failure management and multi-queue optimization. 

🚀 HackHub: Trending AI Tools

💎 vanna-ai/vanna: Toolkit for accurate Text-to-SQL generation via LLMs using RAG to interact with SQL databases through chat.  

💎 dvmazur/mixtral-offloading: Achieve efficient inference for Mixtral-8x7B models, utilizing mixed quantization with HQQ for attention layers and experts, along with a MoE offloading strategy. 

💎 pootiet/explain-then-translate: 2-stage Chain-of-Thought (CoT) prompting technique for program translation to improve translation across various Python-to-X and X-to-X directions. 

💎 genezc/minima: Addresses the challenge of distilling knowledge from large teacher LMs to smaller student ones to optimize the capacity gap for effective LM distillation and achieving competitive performance with resource-efficient models.