AI Distilled 34: Empowering Education Through AI

👋 Hello ,

“The real power that AI brings to education is connecting our learning intelligently to make us smarter in the way we understand ourselves, the world and how we teach and learn.” - Rose Luckin, UCL professor, Co-founder, Institute for Ethical AI in Education 

AI makes learning more inclusive and personalized than ever before. Recent advancements including the launch of Microsoft’s AI-powered Reading Coach and OpenAI’s first-of-its-kind partnership with the Arizona State University will ensure the future of learning is bright. 

Welcome back to a new issue of AI Distilled - your one-stop destination for all things AI, ML, NLP, and Gen AI. Let’s get started with the latest news and developments across sectors: 

To begin with, 

💎 Explore Packt's New Year, New Data Upskilling program – Meet the Datapro Mini Library: an essential, user-friendly platform you can't afford to overlook. 

AI Launches & Industry Updates:  

AI Will Not Displace Humans Anytime Soon, Says MIT Study 

Voice Cloning Startup ElevenLabs Raises $80 Million, Achieves Unicorn Status 

Samsung Introduces New AI Features in Galaxy Phones 

AI Graphic Design Startup Recraft Raises $12 Million 

OpenAI CEO Looking to Establish Own AI Chip Factories 

Meta CEO Mark Zuckerberg Enters Race to Build AGI 

AI in Education: 

OpenAI Signs Deal with Arizona State University 

Microsoft Makes AI-Powered Reading Coach Freely Available 

AI in Healthcare:  

AI to Save Asia-Pacific Healthcare $100 Billion Annually by 2025 

WHO Releases Guidance on Ensuring Ethics of Powerful AI Models 

AI in Finance: 

Survey Finds Majority of Finance Leaders Believe AI Will Boost Productivity 

Singapore Fintech Startup Secures Series A Funding to Automate Accounting 

AI in Supply Chain Management: 

AI and Supply Chain Changes Top Priorities for Apparel Brands in 2024 

We’ve also curated the latest GPT and LLM resources, tutorials, and secret knowledge:  

Discover New Methods for Aligning Chatbots 

New Framework Helps AI Systems Evaluate Their Own Answers 

Making Sense of Time: Understanding the Mathematical Underpinnings of Recurrent Neural Networks 

Detecting Deception: New Methods to Uncover AI Untruths 

Finally, don’t forget to check-out our hands-on tips and strategies from the AI community for you to use on your own projects:  

How to Use RAGxplorer to Help Make Sense of AI Data 

How to Create a Multi-Modal Nutrition Tool 

How to Combine Language Models 

Using Raspberry Pi with Offline Speech and Language Models 

Looking for some inspiration? Here are some GitHub repositories to get your projects going!  

huggingface/nanotron 

tencentarc/visft 

linkdd/aitoolkit 

FlagOpen/TACO 

📥 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." 

📣 And here's the twist – we're tuning into YOUR frequency! Inspired by a reader's request, we're launching a column just for you. Got a burning question or a topic you're itching to dive into? Drop your suggestions in our content box – because your journey of discovery is our blueprint.

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

✨Packt's 2024 Specials✨

Discover Packt's New Year, New Data Upskilling program, designed for data professionals. Gain a competitive edge in data science and analytics with expert-curated resources. Our goal? To help you seamlessly upgrade your skills in the most efficient way possible, enabling you to switch between topics without losing your stride. 

Introducing the Datapro Mini Library: a smooth, user-friendly platform that you simply can't afford to miss. Here’s what our DataPro platform offers: 

On-Demand Learning: Immerse yourself in Packt’s comprehensive data-based knowledge base, featuring hundreds of books, video courses, research papers, and articles. 

Expert Problem Solving: Get bespoke solutions to your most challenging problems, directly from our vast network of data experts and authors. 

Advanced Self-Assessment: Utilize our tools for skill gap analysis and progress tracking, pinpointing areas for improvement and tracking your learning journey. 

Personalized DataPro Dashboard: Keep tabs on your activities, revisit recent learning sections, and receive tailored recommendations to align with your learning objectives. 

Skill Gap Analysis: Deep dive into your SQL, R, Python, and other skills with detailed quizzes and personalized feedback. 

The icing on the cake? Join the thriving community of more than 150 data/AI professionals in our Discord channel. Get exclusive access to our DataPro beta program, and even have a chance to win Amazon gift cards! 

All this is available for just $7.99 per month. Remember Benjamin Franklin's words, "An investment in knowledge pays the best interest." There’s no better time to invest in your professional growth than now. 

Don't miss this opportunity to power up your data journey. Subscribe now and take the first step towards becoming a data mastermind!

⚡ TechWave: AI/GPT News & Analysis

AI Launches & Industry Updates

💎 AI Will Not Displace Humans Anytime Soon, Says MIT Study: A MIT study explored the potential impact of AI, particularly computer vision, on jobs involving visual analysis. The findings suggest that only 23% of wages in these jobs are cost-effective to automate with current AI. Job displacement is expected to be gradual, taking decades to significantly affect employment levels, contrary to some earlier predictions. 

💎 Voice Cloning Startup ElevenLabs Raises $80 Million, Achieves Unicorn Status: ElevenLabs, a voice AI startup, secured $80 million in Series B funding, reaching a $1 billion valuation. Their tech creates realistic voices from text or samples, targeting audiobooks, dubbing, and gaming. While investors highlight its potential, ethical and legal concerns persist regarding voice cloning. 

💎 Samsung Introduces New AI Features in Galaxy Phones: Samsung's Galaxy S24 smartphones now offer AI translation features with up to 13 languages. Users can call, text, and translate live audio and text using Google's Gemini AI model, ensuring private and secure on-device translations, aiding international communication and travelers. 

💎 AI Graphic Design Startup Recraft Raises $12 Million: London's Recraft, an AI graphic design startup, secures $12 million in Series A funding, led by Khosla Ventures and Nat Friedman. Their platform helps brands create visuals from text prompts. With 300,000 users, Recraft aims to develop its own graphic design foundation model, potentially reducing the need for designers as the global design AI market is expected to reach $7.75 billion by 2032. 

💎 OpenAI CEO Looking to Establish Own AI Chip Factories: OpenAI CEO Sam Altman is seeking billions in investment, including $8 billion from G42, to establish his own AI-specific ASIC factories due to concerns about semiconductor foundries' ability to meet future AI chip demand. This move aims to secure OpenAI's access to specialized AI processors and promote industry self-reliance in chip design and manufacturing. 

💎 Meta CEO Mark Zuckerberg Enters Race to Build AGI: Meta CEO Mark Zuckerberg aims to develop artificial general intelligence (AGI), bolstered by 600,000 GPUs by 2024. He plans to integrate AGI into Meta apps and share models openly, though closure is an option if safety or strategic concerns arise in the pursuit of superhuman intelligence. 

AI in Education

💎 OpenAI Signs Deal with Arizona State University: OpenAI signed a deal with Arizona State University to bring its ChatGPT AI chatbot to ASU researchers, staff and faculty. This indicates shifting views on using AI in education as the technology advances. AI has potential benefits for helping students but concerns about plagiarism linger largely unaddressed. 

💎 Microsoft Makes AI-Powered Reading Coach Freely Available: Microsoft offers free access to its AI-based Reading Coach for users with Microsoft accounts. The tool offers personalized reading practice with features like text-to-speech, but experts emphasize the irreplaceable role of teachers in assessing comprehension. 

AI in Healthcare

💎 AI to Save Asia-Pacific Healthcare $100 Billion Annually by 2025: IDC predicts generative AI will save 10% of clinician time in Asia-Pacific (excluding Japan) by 2025, leading to $100 billion in healthcare savings. By 2027, half of healthcare organizations will double AI investments for personalized care. Other forecasts include 30% adopting virtualized work models by 2025 and 60% emphasizing "techquity" partnerships to bridge digital divides. IDC anticipates the next five years shaping a patient-centric, AI-driven healthcare future in the region. 

💎 WHO Releases Guidance on Ensuring Ethics of Powerful AI Models: The WHO releases guidelines for Large Multi-Modal Models (LMMs) in healthcare, highlighting their potential and risks. Over 40 recommendations address responsible development, oversight, and equitable use, emphasizing diversity and safety to protect users and promote health equity. 

AI in Finance

💎 Survey Finds Majority of Finance Leaders Believe AI Will Boost Productivity: A survey by OneStream found 80% of financial decision-makers believe AI will increase productivity in finance departments within five years. AI streamlines data management and improves forecasting, despite challenges like training and data privacy. Finance leaders see AI as a key part of their operations. 

💎 Singapore Fintech Startup Secures Series A Funding to Automate Accounting: Singapore-based AI accounting startup Bluesheets secured $6.5 million in a Series A round led by Illuminate Financial Management, with support from Antler. Bluesheets, founded in 2020, uses ML to simplify financial workflows for businesses, serving 10,000+ customers globally. Despite generating $180,000 in revenue last year, the company incurred $2.39 million in losses while expanding its platform. 

AI in Supply Chain Management

💎 AI and Supply Chain Changes Top Priorities for Apparel Brands in 2024: A survey of 250 apparel and fashion executives reveals that top tech priorities include using AI for marketing and financial forecasting. Many plan to increase onshoring and invest in automation, while also opening and closing stores to focus on smaller formats. 

🔮 Expert Insights from Packt Community 

💎 Unlocking the Secrets of Prompt Engineering - By Gilbert Mizrahi 

"Unlocking the Secrets of Prompt Engineering" is your go-to guide to mastering AI-driven writing with large language models (LLMs). Learn prompt fundamentals, apply LLMs for content creation, chatbots, and coding. Explore practical use cases, from product descriptions to creative writing. Dive into advanced applications, ethics, and best practices. Unlock AI's full potential in writing and boost productivity. Get your copy now and transform your writing skills with AI. 

💎 Building LLM Apps - By Valentina Alto 

This is your comprehensive guide to Large Language Models (LLMs). It covers LLM fundamentals, architectural frameworks like GPT 3.5/4 and Falcon LLM, and introduces LangChain. Learn to create intelligent agents, retrieve unstructured data, and engage with structured data using LLMs. Explore the future of Large Foundation Models (LFMs) extending AI capabilities beyond language. Whether you're an AI expert or newcomer, this book is your roadmap to unleash the power of LLMs. Access the book now and shape the future of intelligent machines. 

💎 Machine Learning for Time Series - Second Edition - By Ben Auffarth 

This latest book offers an elaborative guide to Python time-series packages, aiding in the creation of predictive systems. Covering traditional autoregressive models to modern non-parametric ones, this edition explains loading time-series data, deep learning, convolutional networks, and gradient boosting. New additions include financial market forecasting and case studies. Master time-series analysis with machine learning. Take the first step towards mastering time series analysis - get your copy now. 

🌟 Secret Knowledge: AI/LLM Resources

💎 Discover New Methods for Aligning Chatbots: Hugging Face researchers tested three methods to enhance conversational AI assistants without reinforcement learning: Direct Preference Optimization, Identity Preference Optimization, and Kahneman-Tversky Optimization. Tuning hyperparameters, especially beta, proved crucial for better performance in multi-turn conversations. 

💎 New Framework Helps AI Systems Evaluate Their Own Answers: Google researchers created ASPIRE to enhance LLMs' self-confidence assessment. It fine-tunes models and trains them to self-evaluate. Test results show ASPIRE improves error identification and smaller models using it outperform larger ones. It's a step toward more trustworthy AI in decision-making. 

💎 Making Sense of Time: Understanding the Mathematical Underpinnings of Recurrent Neural Networks: Discover the math behind Recurrent Neural Networks (RNNs), which excel in analyzing sequences like time series. The author explains RNN equations, shows how to build one from scratch in Python, and demonstrates their use in predicting stock prices, revealing their ability to capture time-based patterns. 

💎 Detecting Deception: New Methods to Uncover AI Untruths: Researchers at Kolena used various methods to spot inaccuracies in LLM-generated responses. They achieved over 90% accuracy in detecting errors with context. More techniques like self-consistency testing and involving another AI improved accuracy. 

🔛 Masterclass: AI/LLM Tutorials

💎 How to Use RAGxplorer to Help Make Sense of AI Data: Discover RAGxplorer, a web app for understanding AI data. Upload documents to see how they're analyzed in chunks and their connections to questions. It unveils insights into retrieval-augmented generation (RAG) and is a promising tool for exploring AI training datasets. 

💎 How to Create a Multi-Modal Nutrition Tool: Learn how to develop a smart food journal to help track nutrition and diet goals. The journal allows users to take pictures of meals which are then analyzed using GPT-4 Vision to provide nutritional information. Autogen helps rapidly build the application by leveraging LLMs. A user-friendly interface was created with Gradio. 

💎 How to Combine Language Models: Combine ML models to create a versatile AI. The article explains techniques like weighted averaging and dealing with parameter conflicts. Learn to merge Mistral, WizardMath, and CodeLlama using the mergekit toolkit. 

💎 Raspberry Pi with Offline Speech and Language Models: Discover how to enable AI on a Raspberry Pi without internet. Learn to make the tiny device understand and respond to speech using locally stored LLMs. The article guides setting up Whisper and fine-tuning GPT-2 on the Pi, showing an affordable offline AI solution. 

🚀 HackHub: Trending AI Tools

💎 huggingface/nanotron: Tools for efficiently distributing LLM training across multiple processors via 3D parallelism techniques. 

💎 tencentarc/visft: Two-stage training technique called ViSFT to improve large foundation models on visual tasks. 

💎 linkdd/aitoolkit: The AI Toolkit library provides C++ tools like finite state machines, behavior trees, utility AI and goal-oriented action planning to help developers create intelligent non-player characters for their games.  

💎 FlagOpen/TACO: Topics in Algorithmic COde generation is a dataset containing over 25,000 programming problems to evaluate state-of-the-art models.