Bölümler
-
Nikhil and Piyush welcome their first guest, Rukma Sen, an AI Product Marketing Manager at Google. Rukma shares her unique insights into how AI is transforming marketing strategies and operations, offering a detailed look at how she coaches AI tools to boost productivity and creativity in her role. From designing custom AI workflows to using cutting-edge tools, Rukma discusses the art and science of integrating AI into her job. We discuss Rukma's content creation workflow using a content creator bot together with a content evaluator bot, how she coaches the LLMs to improve their output and how they form a team to interact with each other. Rukma emphasizes the importance of starting with the end goals in mind when creating marketing content and the importance of human judgment and intuition in conjunction with AI tools to enhance productivity and creativity in a goal-oriented manner.
=== ⏰ CHAPTERS ===
0:00 Introducing Rukma and her role as a Product Marketing Manager
19:06 Coaching and Managing AI assistants
32:52 Multi-agent workflows
42:03 Tools to enhance creativity and productivity
=== 🧠 KEY CONCEPTS ===
- The importance of coaching AI: Rukma emphasizes the importance of treating AI tools as "coachees" that require clear instructions and feedback to improve their outputs. This approach can significantly enhance the effectiveness of AI in various marketing tasks.
- Building a team of AI assistants: Using a team of AI assistants such as a content creator bot and a content evaluator bot can streamline the content creation process and ensure high-quality output.
- Exploring "unknown unknowns": The use of frameworks like the Johari Window helps in uncovering blind spots and unknowns in AI-driven projects, leading to more robust and effective outcomes.
- Understand the end goals: Understanding the target audience, event goals, and competitive presence is crucial when creating marketing content. Human judgment and intuition are essential in conjunction with AI tools to achieve the right goals.
=== 🔗 LINKS ===
Rukma Sen
- Linkedin: https://www.linkedin.com/in/rukmasen/
Art and Science of AI
- Homepage: https://artscienceai.substack.com/about
- YouTube: https://www.youtube.com/@ArtScience-AI
- Spotify: https://podcasters.spotify.com/pod/show/art-science-ai
- Linkedin: https://www.linkedin.com/company/art-science-ai
- Facebook: https://www.facebook.com/ArtScienceAI
- Instagram: http://instagram.com/artscienceai/
- Threads: https://www.threads.net/@artscienceai
- Twitter / X: https://x.com/ArtScienceAI
=== 💬 KEYWORDS ===
#AI #GenAI #LLM #ChatGPT #podcast
-
In this episode, Nikhil and Piyush delve into the latest happenings in the world of AI focusing on Apple Intelligence, Meta AI, and OpenAI's SearchGPT. We discuss the recent delays in Apple Intelligence, the growing trend of companies over-promising and under-delivering on AI features, and the impact of European Union regulations on tech giants. We explore Meta’s significant advancements in open-source AI with LLAMA 3.1, Meta's strategy of commoditizing AI, and the implications of this shift for the industry. We also discuss the launch of OpenAI's Search GPT and its potential impact on the search industry.
=== ⏰ CHAPTERS ===
00:00: Apple Intelligence delays and impacts
09:29: European Union regulations and impact on AI
20:04: Meta’s Open Source AI and Industry Implications
39:26: OpenAI's SearchGPT and the future of AI search
45:30: The Innovator's Dilemma: Balancing Innovation and Existing Business
=== 🧠 KEY CONCEPTS ===
- Apple AI Delays: Apple’s new AI features, initially planned for the iPhone 15 Pro launch, are delayed due to security and privacy issues, pushing some features to next year.
- European Union excluded from big tech AI launches: The European Union’s stringent regulations, like the Digital Markets Act, are causing tech giants like Apple and Meta to delay or withhold AI features in the region, impacting innovation.
- Meta’s Open Source Move: Meta’s release of LLAMA 3.1 highlights the rapid advancements in open-source AI, challenging the dominance of closed-source models from companies like OpenAI.
- AI Model Commoditization: The competitive landscape suggests that the value of proprietary AI models may diminish as open-source alternatives quickly catch up, pushing companies to focus on unique applications and user experiences.
- Future of AI Search: The introduction of OpenAI’s Search GPT presents a potential disruption to traditional search engines, emphasizing the need for incumbents like Google to adapt to evolving AI-driven search experiences.
=== 🔗 LINKS ===
- Homepage: https://artscienceai.substack.com/about
- YouTube: https://www.youtube.com/@ArtScience-AI
- Spotify: https://podcasters.spotify.com/pod/show/art-science-ai
- Linkedin: https://www.linkedin.com/company/art-science-ai
- Facebook: https://www.facebook.com/ArtScienceAI
- Instagram: http://instagram.com/artscienceai/
- Threads: https://www.threads.net/@artscienceai
- Twitter / X: https://x.com/ArtScienceAI
=== 💬 KEYWORDS ===
#AI #GenAI #LLM #ChatGPT #podcast
-
Eksik bölüm mü var?
-
In this episode, Nikhil and Piyush discuss the fear of AI leading to mass unemployment. We consider historical precedents such as the Industrial Revolution and the advent of Personal Computers to understand how past technological revolutions led to both job loss as well as new job creation. We consider whether this time is truly different with the AI revolution, the societal implications of these changes, and the importance of jobs as not only a source of economic value, but also as a key source of meaning in the modern world.
= ⏰ CHAPTERS =
00:00: Introduction
03:32: Historical parallel 1 - the Industrial Revolution
09:36: Historical parallel 2 - the Personal Computer revolution
17:54: AI's impact on the future of work
28:35: Societal implications= 🧠 KEY CONCEPTS =
Historical Context: The Industrial Revolution of the 1800s and the Personal Computer Revolution of the 1990s are two important historical parallels to help us understand the AI revolution. Job loss and new job creation: Technological revolutions in the past have led to the loss of many jobs as well as the creation of many new jobs that did not previously exist (e.g. software engineering). AGI Concerns: The potential arrival of Artificial General Intelligence (AGI) raises unique concerns about the future of all jobs, posing questions about the role of humans in a fully automated world. Societal Rebalancing: Technological upheavals historically cause short-term societal disruptions but eventually lead to new equilibria. The current AI wave may require new societal models, such as Universal Basic Income, to address economic disparities. Meaning and Value: The need to reconsider how we assign value and meaning to work in a society increasingly driven by AI capabilities, moving beyond purely economic contributions.= 🔗 LINKS =
Homepage: https://artscienceai.substack.com/about YouTube: https://www.youtube.com/@ArtScience-AI Spotify: https://podcasters.spotify.com/pod/show/art-science-ai Linkedin: https://www.linkedin.com/company/art-science-ai Facebook: https://www.facebook.com/ArtScienceAI Instagram: http://instagram.com/artscienceai/ Threads: https://www.threads.net/@artscienceai Twitter / X: https://x.com/ArtScienceAI= 💬 KEYWORDS =
#AI #GenAI #LLM #ChatGPT #podcast -
In this episode, Piyush and Nikhil explore the AI value chain. We explore the different components that go into delivering an AI application from start to finish, including the compute layer, the foundational model layer, and the application layer. Drawing analogies to traditional supply chains, we discuss how companies like NVIDIA, OpenAI, Google, Microsoft, etc. fit into this ecosystem. Tune in to understand the intricacies of AI development and the roles various players have in this rapidly evolving field.
=== ⏰ CHAPTERS ===
00:00: Introducing the concept of a Value Chain
08:37: The Value Chain of traditional software applications
25:41: Value Chain of AI: compute, models, and applications
44:04: Broader considerations in the value chain: environmental impact, closed-source vs. open-source, etc.
=== 🧠 KEY CONCEPTS ===
- The AI Value Chain: The value chain for AI includes three main layers: compute (hardware and cloud), foundational models, and applications. Each layer involves different companies and technologies that add value to the end product.
- Compute Layer: NVIDIA GPUs play a crucial role in AI model training due to their efficiency in neural computing. Cloud companies like AWS, Google Cloud, and Microsoft Azure provide the infrastructure for training and deploying these models.
- Foundational Models: Training AI models is resource-intensive, requiring vast amounts of data and computational power. There is a distinction between open source and closed source models, impacting how developers can use and customize them.
- Application Layer: Applications built on AI can either integrate their own models or rely on existing ones. The value of AI in applications depends on the balance between computational cost and the value added to the user experience.
- Energy Consumption: AI's growing energy demands pose environmental challenges, potentially driving innovations in sustainable energy solutions, including nuclear energy.
=== 🔗 LINKS ===
- Homepage: https://artscienceai.substack.com/about
- YouTube: https://www.youtube.com/@ArtScience-AI
- Spotify: https://podcasters.spotify.com/pod/show/art-science-ai
- Linkedin: https://www.linkedin.com/company/art-science-ai
- Facebook: https://www.facebook.com/ArtScienceAI
- Instagram: http://instagram.com/artscienceai/
- Threads: https://www.threads.net/@artscienceai
- Twitter / X: https://x.com/ArtScienceAI
=== 💬 KEYWORDS ===
#AI #GenAI #LLM #ChatGPT #podcast
-
In this episode we discuss how to go beyond mastering ChatGPT to automating your tasks using AI APIs. We introduce the concept of APIs (Application Programming Interfaces) and how they can be used to automate tasks to help you free up your time and scale up your productivity. Nikhil gives a live demo of an AI automation tool he built to help automate repetitive parts of Piyush's workflow as a sales executive, where he has to manually conduct research on each new client to prepare for sales meetings. The automation transforms a labor-intensive process into a seamless workflow, which saves time and improves productivity for sales executives like Piyush. We explore the technical aspects of API integration and discuss the broader implications of AI in personal productivity. Whether you're in sales, tech, or just curious about AI, this episode offers valuable insights into making AI work for you.
=== ⏰ CHAPTERS ===
00:00: Benefits of automation
07:59: Understanding APIs and the AI ecosystem
24:33: Automating Piyush's sales research
38:04: Exploring Use Cases for AI and Automation
51:38: AI automation for personal productivity
=== 🧠 KEY CONCEPTS ===
- Importance of Automation: Automation frees up time and increases productivity by enabling repetitive tasks to be done in the background
- Importance of APIs (Application Programming Interfaces): APIs allow different applications to interact with each other without human intervention.
- The role of programming: No-code platforms such as Zapier and Make enable users to create automation workflows without any programming knowledge. But these platforms are limited, and having some basic programming knowledge enables you to leverage the full power of AI and APIs for automation.
- Use cases for automation: Nikhil gives a live demo of an AI automation tool he built to help automate repetitive parts of Piyush's workflow as a sales executive, where he has to manually conduct research on each new client to prepare for sales meetings. The same concept can be extended to automate a wide range of workflows.
=== 🔗 LINKS ===
- Homepage: https://artscienceai.substack.com/about
- YouTube: https://www.youtube.com/@ArtScience-AI
- Spotify: https://podcasters.spotify.com/pod/show/art-science-ai
- Linkedin: https://www.linkedin.com/company/art-science-ai- Facebook: https://www.facebook.com/ArtScienceAI
- Instagram: http://instagram.com/artscienceai/
- Threads: https://www.threads.net/@artscienceai
- Twitter / X: https://x.com/ArtScienceAI
=== 💬 KEYWORDS ===
#AI #GenAI #LLM #ChatGPT #podcast
-
This episode covers practical applications of AI in everyday life, from simple email drafting to sophisticated company research. We discuss different prompting techniques such as few-shot prompting and chain of thought prompting to improve the quality and accuracy of AI-generated responses. We also discuss custom instructions, custom GPTs, and explore the powerful potential of AI in automating repetitive tasks. Tune in to discover how you can harness the power of AI to enhance productivity and streamline your workflows.
=== ⏰ CHAPTERS ===
00:00: Introduction
08:02: Getting Started with AI and Identifying Tasks and Workflows
13:51: General-Purpose AI vs. Purpose-Built AI
27:30: Examples of ChatGPT usage
31:20: Prompt engineering
48:10: Custom instructions and custom GPTs
=== 🧠 KEY CONCEPTS ===
- Identifying AI Use Cases: Look for tasks in your life that are repeatable, time-consuming, and frustrating to see where AI can help.
- General Purpose AI vs. Purpose-Built AI: General purpose AI (e.g. ChatGPT) is great for a wide range of tasks, while purpose-built AI (e.g. Adobe Acrobat AI) can be more efficient for specific tasks and workflows.
- Prompt Engineering: The quality of AI output is significantly improved with well-crafted prompts. Use the few-shot prompting technique by giving examples to guide the AI model's response.
- Chain of Thought Prompting: Encouraging AI to think out loud and show its reasoning can lead to more accurate and thoughtful responses.
- Custom GPTs: Creating custom GPTs tailored to specific tasks can save time and increase efficiency. This involves setting custom instructions, uploading relevant files, and enabling specific capabilities.
=== 🔗 LINKS ===
- Homepage: https://artscienceai.substack.com/about
- YouTube: https://www.youtube.com/@ArtScience-AI
- Spotify: https://podcasters.spotify.com/pod/show/art-science-ai
- Linkedin: https://www.linkedin.com/company/art-science-ai
- Facebook: https://www.facebook.com/ArtScienceAI
- Instagram: http://instagram.com/artscienceai/
- Threads: https://www.threads.net/@artscienceai
- Twitter / X: https://x.com/ArtScienceAI
=== 💬 KEYWORDS ===
#AI #ArtificialIntelligence #GenerativeAI #GenAI #PromptEngineering #LLM #MachineLearning #ML #tech #podcast
-
Your one-stop-shop for all things Apple Intelligence! In this episode, we discuss the Apple Intelligence announcements from WWDC 2024. We discuss new AI capabilities in Apple’s apps and in Siri, the all-new AI assistant that can perform actions across multiple apps. We deep-dive into the architecture of Apple Intelligence, with a focus on privacy, and we discuss the implications of Apple Intelligence for users, developers, and the overall AI ecosystem.
-
In this episode we discuss the hype around AI and the challenges in achieving its full potential in 2024. The last 10% of solving problems with AI has proven to be difficult due to LLM hallucinations and reliability challenges. We discuss how this problem can be addressed by grounding LLMs with a knowledge base via the paradigm of Retrieval Augmented Generation (RAG). We discuss the different approaches to working with language models, including training from scratch, fine-tuning, and using RAG, and the opportunities for entrepreneurs in the AI space.
Takeaways
Generative AI may be the next major platform since the internet and mobile, but we are coming down from the peak of inflated expectations of the Gen AI hype cycle LLMs are general purpose models, and when asked domain-specific questions, LLMs tend to “hallucinate” (i.e. generate plausible-sounding answers) rather than admit ignorance Grounding in facts and providing relevant context can help mitigate the hallucination problem. Retrieval Augmented Generation (RAG) is a common paradigm for grounding LLMs in facts. As AI models and agents become commoditized and democratized, competitive moats will be built around proprietary data and tailored user experiences -
Welcome to season 2 of Art and Science of AI! In this episode we reflect on our journey since season 1 last year. We discuss the impact of understanding AI on Piyush’s career in ad sales at Google. It enabled him to reimagine his job as selling AI rather than just selling ads. We also discuss the increasing importance of AI for Nikhil’s work as a Product Manager at Meta, and reflect on whether “AI is eating the world”!
=== 🔗 REFERENCES ===
- Art and Science of AI: https://ArtScienceAI.substack.com
- Nikhil Maddirala: https://www.linkedin.com/in/nikhilmaddirala/
- Piyush Agarwal: https://www.linkedin.com/in/piyush5/
- “Why software is eating the world” by Marc Andreessen: https://a16z.com/why-software-is-eating-the-world/
=== 💬 KEYWORDS ===
#AI #ArtificialIntelligence #GenerativeAI #GenAI #LLM #MachineLearning #ML #tech
-
In this episode we consider whether AI is having its "iPhone moment" as proclaimed by Nvidia’s CEO. The launch of the iPhone revolutionized the ways in which people interact with business and society, paving the way for innovative new businesses and social experiences such as Uber and Instagram. Will the rise of AI assistants and agents lead to a similar revolution? We discuss the evolution of AI, the dominance of big tech companies, and opportunities for entrepreneurs in this rapidly changing landscape.
=== ⏰ CHAPTERS ===
00:00: Preview and intro
01:25: AI’s iPhone moment
08:00: ChatGPT plugins and entrepreneurship opportunities
16:17: Dominance of big tech in AI
23:17: AI industry landscape
=== 🔗 REFERENCES ===
Art and Science of AI: ArtScienceAI.substack.com (detailed show notes and full episode transcripts)
Nikhil Maddirala: https://www.linkedin.com/in/nikhilmaddirala/
Piyush Agarwal: https://www.linkedin.com/in/piyush5/
=== 💬 KEYWORDS ===
#AI #ArtificialIntelligence #GenerativeAI #GenAI #LLM #MachineLearning #ML #tech #podcast
-
In this episode we discuss the limitations of ChatGPT such as its lack of up-to-date knowledge, lack of private / domain specific knowledge, and lack of tool use abilities. We then discuss innovative new solutions to these problems such as vector database retrieval, ChatGPT plugins, and AI agents with access to external tools that can orchestrate complex tasks and workflows autonomously. What are the implications for business and society? We also touch upon some criticisms of OpenAI’s convoluted governance structure and lack of transparency into their model training and data sources.
-
In this episode we delve into the world of generative AI with a focus on language modeling. We explore how text is transformed into semantically meaningful data through the use of vector embeddings, providing an in-depth look at the mechanics behind AI models like Open AI’s GPT-3. Discover the complexities of semantic relationships in language, the role of mathematical concepts in AI, and the advancements that make generative AI both powerful and conversational.
-
In this episode we go beyond classical machine learning into the fascinating world of neural networks. We discuss how neural networks, inspired by the human brain, revolutionize our ability to process unstructured data like images and text. Using a detailed example of handwriting digit recognition, we break down how neural networks learn patterns, make predictions, and transform raw data into valuable insights. Tune in to explore the magic of hidden layers, the significance of activation functions, and the trade-offs between model power and interpretability in modern AI systems.
-
In this episode, we dive into the fundamentals of AI, starting with its basic definition and exploring how it has evolved over time. We discuss the differences between two approaches to AI — rule based systems and machine learning — using examples such as classification for spam filtering and linear regression for house price prediction. We dive deeper into classical machine learning, introducing the concepts of model architecture, features, parameters, objective functions, and training algorithms. We conclude by considering some of the limitations of classical machine learning, and the rise of neural networks.
-
In this introductory episode of Art and Science of AI we discuss our background, expertise, and motivation for embarking on this journey to demystify AI! Piyush shares his fascination with seemingly magical AI technologies like ChatGPT and MidJourney, and his desire to understand the underlying mechanics. Nikhil shares his background in AI, and his plan for demystifying ChatGPT in this season: starting with the basics of Artificial Intelligence (AI) and Machine Learning (ML), we will demystify key concepts such as neural networks, deep learning, and Large Language Models (LLMs). We will also explore the exciting potential of ChatGPT and its implications for business and society. Note: Season 1 was originally recorded back in May 2023 as a continuous 3-hour long conversation. Season 2 is now live, so please subscribe for new episodes every week! artscienceai.substack.com
=== 🔗 REFERENCES ===
Art and Science of AI: ArtScienceAI.substack.com
Nikhil Maddirala: https://www.linkedin.com/in/nikhilmaddirala/
Piyush Agarwal: https://www.linkedin.com/in/piyush5/
=== 💬 KEYWORDS ===
#ChatGPT #AI #ML #ArtificialIntelligence #MachineLearning #LLM #tech
