AI Engineering Podcast
AI Engineering Podcast

AI Engineering Podcast

Tobias Macey

Overview
Episodes

Details

This show is your guidebook to building scalable and maintainable AI systems. You will learn how to architect AI applications, apply AI to your work, and the considerations involved in building or customizing new models. Everything that you need to know to deliver real impact and value with machine learning and artificial intelligence.

Recent Episodes

Enhancing AI Retrieval with Knowledge Graphs: A Deep Dive into GraphRAG
SEP 10, 2024
Enhancing AI Retrieval with Knowledge Graphs: A Deep Dive into GraphRAG
Summary<br />In this episode of the AI Engineering podcast, Philip Rathle, CTO of Neo4J, talks about the intersection of knowledge graphs and AI retrieval systems, specifically Retrieval Augmented Generation (RAG). He delves into GraphRAG, a novel approach that combines knowledge graphs with vector-based similarity search to enhance generative AI models. Philip explains how GraphRAG works by integrating a graph database for structured data storage, providing more accurate and explainable AI responses, and addressing limitations of traditional retrieval systems. The conversation covers technical aspects such as data modeling, entity extraction, and ontology use cases, as well as the infrastructure and workflow required to support GraphRAG, setting the stage for innovative applications across various industries.<br /><br />Announcements<br /><ul><li>Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems</li><li>Your host is Tobias Macey and today I'm interviewing Philip Rathle about the application of knowledge graphs in AI retrieval systems</li></ul>Interview<br /><ul><li>Introduction</li><li>How did you get involved in machine learning?</li><li>Can you describe what GraphRAG is?<ul><li>What are the capabilities that graph structures offer beyond vector/similarity-based retrieval methods of prompting?</li></ul></li><li>What are some examples of the ways that semantic limitations of nearest-neighbor vector retrieval fail to provide relevant results?</li><li>What are the technical requirements to implement graph-augmented retrieval?<ul><li>What are the concrete ways in which the embedding and retrieval steps of a typical RAG pipeline need to be modified to account for the addition of the graph?</li></ul></li><li>Many tutorials for building vector-based knowledge repositories skip over considerations around data modeling. For building a graph-based knowledge repository there obviously needs to be a bit more work put in. What are the key design choices that need to be made for implementing the graph for an AI application?<ul><li>How does the selection of the ontology/taxonomy impact the performance and capabilities of the resulting application?</li></ul></li><li>Building a fully functional knowledge graph can be a significant undertaking on its own. How can LLMs and AI models help with the construction and maintenance of that knowledge repository?<ul><li>What are some of the validation methods that should be brought to bear to ensure that the resulting graph properly represents the knowledge domain that you are trying to model?</li></ul></li><li>Vector embedding and retrieval are a core building block for a majority of AI application frameworks. How much support do you see for GraphRAG in the ecosystem?<ul><li>For the case where someone is using a framework that does not explicitly implement GraphRAG techniques, what are some of the implementation strategies that you have seen be most effective for adding that functionality?</li></ul></li><li>What are some of the ways that the combination of vector search and knowledge graphs are useful independent of their combination with language models?</li><li>What are the most interesting, innovative, or unexpected ways that you have seen GraphRAG used?</li><li>What are the most interesting, unexpected, or challenging lessons that you have learned while working on GraphRAG applications?</li><li>When is GraphRAG the wrong choice?</li><li>What are the opportunities for improvement in the design and implementation of graph-based retrieval systems?</li></ul>Contact Info<br /><ul><li><a href="https://www.linkedin.com/in/prathle/" target="_blank">LinkedIn</a></li></ul>Parting Question<br /><ul><li>From your perspective, what are the biggest gaps in tooling, technology, or training for AI systems today?</li></ul>Closing Announcements<br /><ul><li>Thank you for listening! Don't forget to check out our other shows. The <a href="https://www.dataengineeringpodcast.com" target="_blank">Data Engineering Podcast</a> covers the latest on modern data management. <a href="https://www.pythonpodcast.com" target="_blank">Podcast.__init__</a> covers the Python language, its community, and the innovative ways it is being used.</li><li>Visit the <a href="https://www.aiengineeringpodcast.com" target="_blank">site</a> to subscribe to the show, sign up for the mailing list, and read the show notes.</li><li>If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.</li><li>To help other people find the show please leave a review on <a href="https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243" target="_blank">iTunes</a> and tell your friends and co-workers.</li></ul>Links<br /><ul><li><a href="https://neo4j.com/" target="_blank">Neo4J</a></li><li><a href="https://neo4j.com/blog/graphrag-manifesto/" target="_blank">GraphRAG Manifesto</a></li><li><a href="https://github.blog/ai-and-ml/generative-ai/what-is-retrieval-augmented-generation-and-what-does-it-do-for-generative-ai/" target="_blank">RAG == Retrieval Augmented Generation</a><ul><li><a href="https://www.aiengineeringpodcast.com/retrieval-augmented-generation-implementation-episode-34" target="_blank">Podcast Episode</a></li></ul></li><li><a href="https://en.wikipedia.org/wiki/Very_large_database" target="_blank">VLDB == Very Large DataBases</a></li><li><a href="https://en.wikipedia.org/wiki/Knowledge_graph" target="_blank">Knowledge Graph</a></li><li><a href="https://en.wikipedia.org/wiki/Nearest_neighbor_search" target="_blank">Nearest Neighbor Search</a></li><li><a href="https://en.wikipedia.org/wiki/PageRank" target="_blank">PageRank</a></li><li><a href="https://blog.google/products/search/introducing-knowledge-graph-things-not/" target="_blank">Things Not Strings</a>) Google Knowledge Graph Paper</li><li><a href="https://github.com/pgvector/pgvector" target="_blank">pgvector</a></li><li><a href="https://www.pinecone.io/" target="_blank">Pinecone</a><ul><li><a href="https://www.dataengineeringpodcast.com/pinecone-vector-database-similarity-search-episode-189/" target="_blank">Data Engineering Podcast Episode</a></li></ul></li><li><a href="https://neo4j.com/docs/getting-started/data-modeling/relational-to-graph-modeling/" target="_blank">Tables To Labels</a></li><li><a href="https://en.wikipedia.org/wiki/Natural_language_processing" target="_blank">NLP == Natural Language Processing</a></li><li><a href="https://graph.build/resources/ontology" target="_blank">Ontology</a></li><li><a href="https://www.langchain.com/" target="_blank">LangChain</a></li><li><a href="https://www.llamaindex.ai/" target="_blank">LlamaIndex</a></li><li><a href="https://en.wikipedia.org/wiki/Reinforcement_learning_from_human_feedback" target="_blank">RLHF == Reinforcement Learning with Human Feedback</a></li><li><a href="https://senzing.com/" target="_blank">Senzing</a></li><li><a href="https://neo4j.com/labs/genai-ecosystem/neoconverse/" target="_blank">NeoConverse</a></li><li><a href="https://en.wikipedia.org/wiki/Cypher_(query_language" target="_blank">Cypher</a> query language</li><li><a href="https://www.gqlstandards.org/" target="_blank">GQL</a> query standard</li><li><a href="https://aws.amazon.com/bedrock/" target="_blank">AWS Bedrock</a></li><li><a href="https://cloud.google.com/vertex-ai" target="_blank">Vertex AI</a></li><li><a href="https://www.sequoiacap.com/podcast/training-data-sebastian-siemiatkowski/" target="_blank">Sequoia Training Data - Klarna episode</a></li><li><a href="https://en.wikipedia.org/wiki/Ouroboros" target="_blank">Ouroboros</a></li></ul>The intro and outro music is from <a href="https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/" target="_blank">Hitman's Lovesong feat. Paola Graziano</a> by <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/" target="_blank">The Freak Fandango Orchestra</a>/<a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">CC BY-SA 3.0</a>
play-circle
59 MIN
Harnessing Generative AI for Effective Digital Advertising Campaigns
SEP 2, 2024
Harnessing Generative AI for Effective Digital Advertising Campaigns
Summary<br />In this episode of the AI Engineering podcast Praveen Gujar, Director of Product at LinkedIn, talks about the applications of generative AI in digital advertising. He highlights the key areas of digital advertising, including audience targeting, content creation, and ROI measurement, and delves into how generative AI is revolutionizing these aspects. Praveen shares successful case studies of generative AI in digital advertising, including campaigns by Heinz, the Barbie movie, and Maggi, and discusses the potential pitfalls and risks associated with AI-powered tools. He concludes with insights into the future of generative AI in digital advertising, highlighting the importance of cultural transformation and the synergy between human creativity and AI.<br />Announcements<br /><ul><li>Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems</li><li>Your host is Tobias Macey and today I'm interviewing Praveen Gujar about the applications of generative AI in digital advertising</li></ul>Interview<br /><ul><li>Introduction</li><li>How did you get involved in machine learning?</li><li>Can you start by defining "digital advertising" for the scope of this conversation?<ul><li>What are the key elements/characteristics/goals of digital avertising?</li></ul></li><li>In the world before generative AI, what did a typical end-to-end advertising campaign workflow look like?<ul><li>What are the stages of that workflow where generative AI are proving to be most useful?<ul><li>How do the current limitations of generative AI (e.g. hallucinations, non-determinism) impact the ways in which they can be used?</li></ul></li></ul></li><li>What are the technological and organizational systems that need to be implemented to effectively apply generative AI in public-facing applications that are so closely tied to brand/company image?<ul><li>What are the elements of user education/expectation setting that are necessary when working with marketing/advertising personnel to help avoid damage to the brands?</li></ul></li><li>What are some examples of applications for generative AI in digital advertising that have gone well?<ul><li>Any that have gone wrong?</li></ul></li><li>What are the most interesting, innovative, or unexpected ways that you have seen generative AI used in digital advertising?</li><li>What are the most interesting, unexpected, or challenging lessons that you have learned while working on digital advertising applications of generative AI?</li><li>When is generative AI the wrong choice?</li><li>What are your future predictions for the use of generative AI in dgital advertising?</li></ul>Contact Info<br /><ul><li><a href="https://www.praveengujar.com/" target="_blank">Website</a></li><li><a href="https://www.linkedin.com/in/praveengujar/" target="_blank">LinkedIn</a></li></ul>Parting Question<br /><ul><li>From your perspective, what is the biggest barrier to adoption of machine learning today?</li></ul>Closing Announcements<br /><ul><li>Thank you for listening! Don't forget to check out our other shows. The <a href="https://www.dataengineeringpodcast.com" target="_blank">Data Engineering Podcast</a> covers the latest on modern data management. <a href="https://www.pythonpodcast.com" target="_blank">Podcast.__init__</a> covers the Python language, its community, and the innovative ways it is being used.</li><li>Visit the <a href="https://www.aiengineeringpodcast.com" target="_blank">site</a> to subscribe to the show, sign up for the mailing list, and read the show notes.</li><li>If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.</li><li>To help other people find the show please leave a review on <a href="https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243" target="_blank">iTunes</a> and tell your friends and co-workers.</li></ul>Links<br /><ul><li><a href="https://generativeai.net/" target="_blank">Generative AI</a></li><li><a href="https://en.wikipedia.org/wiki/Large_language_model" target="_blank">LLM == Large Language Model</a></li><li><a href="https://openai.com/index/dall-e/" target="_blank">Dall-E</a>)</li><li><a href="https://en.wikipedia.org/wiki/Reinforcement_learning_from_human_feedback" target="_blank">RLHF == Reinforcement Learning fHuman Feedback</a></li></ul>The intro and outro music is from <a href="https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/" target="_blank">Hitman's Lovesong feat. Paola Graziano</a> by <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/" target="_blank">The Freak Fandango Orchestra</a>/<a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">CC BY-SA 3.0</a>
play-circle
41 MIN
Building Scalable ML Systems on Kubernetes
AUG 15, 2024
Building Scalable ML Systems on Kubernetes
Summary<br />In this episode of the AI Engineering podcast, host Tobias Macy interviews Tammer Saleh, founder of SuperOrbital, about the potentials and pitfalls of using Kubernetes for machine learning workloads. The conversation delves into the specific needs of machine learning workflows, such as model tracking, versioning, and the use of Jupyter Notebooks, and how Kubernetes can support these tasks. Tammer emphasizes the importance of a unified API for different teams and the flexibility Kubernetes provides in handling various workloads. Finally, Tammer offers advice for teams considering Kubernetes for their machine learning workloads and discusses the future of Kubernetes in the ML ecosystem, including areas for improvement and innovation.<br />Announcements<br /><ul><li>Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems</li><li>Your host is Tobias Macey and today I'm interviewing Tammer Saleh about the potentials and pitfalls of using Kubernetes for your ML workloads.</li></ul>Interview<br /><ul><li>Introduction</li><li>How did you get involved in Kubernetes?</li><li>For someone who is unfamiliar with Kubernetes, how would you summarize it?</li><li>For the context of this conversation, can you describe the different phases of ML that we're talking about?</li><li>Kubernetes was originally designed to handle scaling and distribution of stateless processes. ML is an inherently stateful problem domain. What challenges does that add for K8s environments?</li><li>What are the elements of an ML workflow that lend themselves well to a Kubernetes environment?</li><li>How much Kubernetes knowledge does an ML/data engineer need to know to get their work done?</li><li>What are the sharp edges of Kubernetes in the context of ML projects?</li><li>What are the most interesting, unexpected, or challenging lessons that you have learned while working with Kubernetes?</li><li>When is Kubernetes the wrong choice for ML?</li><li>What are the aspects of Kubernetes (core or the ecosystem) that you are keeping an eye on which will help improve its utility for ML workloads?</li></ul>Contact Info<br /><ul><li><a target="_blank">Email</a></li><li><a href="https://www.linkedin.com/in/tammersaleh/" target="_blank">LinkedIn</a></li></ul>Parting Question<br /><ul><li>From your perspective, what is the biggest gap in the tooling or technology for ML workloads today?</li></ul>Links<br /><ul><li><a href="https://superorbital.io" target="_blank">SuperOrbital</a></li><li><a href="https://www.cloudfoundry.org/" target="_blank">CloudFoundry</a></li><li><a href="https://www.heroku.com/" target="_blank">Heroku</a></li><li><a href="https://12factor.net/" target="_blank">12 Factor Model</a></li><li><a href="https://kubernetes.io/" target="_blank">Kubernetes</a></li><li><a href="https://docs.docker.com/compose/" target="_blank">Docker Compose</a></li><li><a href="https://superorbital.io/training/core-kubernetes/" target="_blank">Core K8s Class</a></li><li><a href="https://jupyter.org/" target="_blank">Jupyter Notebook</a></li><li><a href="https://www.crossplane.io/" target="_blank">Crossplane</a></li><li><a href="https://www.dndbeyond.com/monsters/16967-ochre-jelly" target="_blank">Ochre Jelly</a></li><li><a href="https://landscape.cncf.io/" target="_blank">CNCF (Cloud Native Computing Foundation) Landscape</a></li><li><a href="https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/" target="_blank">Stateful Set</a></li><li><a href="https://github.blog/ai-and-ml/generative-ai/what-is-retrieval-augmented-generation-and-what-does-it-do-for-generative-ai/" target="_blank">RAG == Retrieval Augmented Generation</a><ul><li><a href="https://www.aiengineeringpodcast.com/retrieval-augmented-generation-implementation-episode-34" target="_blank">Podcast Episode</a></li></ul></li><li><a href="https://www.kubeflow.org/" target="_blank">Kubeflow</a></li><li><a href="https://flyte.org/" target="_blank">Flyte</a><ul><li><a href="https://www.dataengineeringpodcast.com/flyte-data-orchestration-machine-learning-episode-291" target="_blank">Data Engineering Podcast Episode</a></li></ul></li><li><a href="https://www.pachyderm.com/" target="_blank">Pachyderm</a><ul><li><a href="https://www.dataengineeringpodcast.com/epsiode-1-pachyderm-with-daniel-whitenack" target="_blank">Data Engineering Podcast Episode</a></li></ul></li><li><a href="https://www.coreweave.com/" target="_blank">CoreWeave</a></li><li><a href="https://kubernetes.io/docs/reference/kubectl/" target="_blank">Kubectl ("koob-cuddle")</a></li><li><a href="https://helm.sh/" target="_blank">Helm</a></li><li><a href="https://kubernetes.io/docs/concepts/extend-kubernetes/api-extension/custom-resources/" target="_blank">CRD == Custom Resource Definition</a></li><li><a href="https://horovod.ai/" target="_blank">Horovod</a><ul><li><a href="https://www.pythonpodcast.com/ludwig-horovod-distributed-declarative-deep-learning-episode-341" target="_blank">Podcast.__init__ Episode</a></li></ul></li><li><a href="https://temporal.io/" target="_blank">Temporal</a></li><li><a href="https://slurm.schedmd.com/overview.html" target="_blank">Slurm</a></li><li><a href="https://www.ray.io/" target="_blank">Ray</a></li><li><a href="https://www.dask.org/" target="_blank">Dask</a></li><li><a href="https://en.wikipedia.org/wiki/InfiniBand" target="_blank">Infiniband</a></li></ul>The intro and outro music is from <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Love_death_and_a_drunken_monkey/04_-_The_Hug" target="_blank">The Hug</a> by <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/" target="_blank">The Freak Fandango Orchestra</a> / <a href="http://creativecommons.org/licenses/by-sa/3.0/" target="_blank">CC BY-SA</a>
play-circle
50 MIN
Expert Insights On Retrieval Augmented Generation And How To Build It
JUL 28, 2024
Expert Insights On Retrieval Augmented Generation And How To Build It
Summary<br />In this episode we're joined by Matt Zeiler, founder and CEO of Clarifai, as he dives into the technical aspects of retrieval augmented generation (RAG). From his journey into AI at the University of Toronto to founding one of the first deep learning AI companies, Matt shares his insights on the evolution of neural networks and generative models over the last 15 years. He explains how RAG addresses issues with large language models, including data staleness and hallucinations, by providing dynamic access to information through vector databases and embedding models. Throughout the conversation, Matt and host Tobias Macy discuss everything from architectural requirements to operational considerations, as well as the practical applications of RAG in industries like intelligence, healthcare, and finance. Tune in for a comprehensive look at RAG and its future trends in AI.<br />Announcements<br /><ul><li>Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems</li><li>Your host is Tobias Macey and today I'm interviewing Matt Zeiler, Founder &amp; CEO of Clarifai, about the technical aspects of RAG, including the architectural requirements, edge cases, and evolutionary characteristics</li></ul>Interview<br /><ul><li>Introduction</li><li>How did you get involved in the area of data management?</li><li>Can you describe what RAG (Retrieval Augmented Generation) is?</li><li>What are the contexts in which you would want to use RAG?</li><li>What are the alternatives to RAG?</li><li>What are the architectural/technical components that are required for production grade RAG?</li><li>Getting a quick proof-of-concept working for RAG is fairly straightforward. What are the failures modes/edge cases that start to surface as you scale the usage and complexity?</li><li>The first step of building the corpus for RAG is to generate the embeddings. Can you talk through the planning and design process? (e.g. model selection for embeddings, storage capacity/latency, etc.)</li><li>How does the modality of the input/output affect this and downstream decisions? (e.g. text vs. image vs. audio, etc.)</li><li>What are the features of a vector store that are most critical for RAG?</li><li>The set of available generative models is expanding and changing at breakneck speed. What are the foundational aspects that you look for in selecting which model(s) to use for the output?</li><li>Vector databases have been gaining ground for search functionality, even without generative AI. What are some of the other ways that elements of RAG can be re-purposed?</li><li>What are the most interesting, innovative, or unexpected ways that you have seen RAG used?</li><li>What are the most interesting, unexpected, or challenging lessons that you have learned while working on RAG?</li><li>When is RAG the wrong choice?</li><li>What are the main trends that you are following for RAG and its component elements going forward?</li></ul>Contact Info<br /><ul><li><a href="https://www.matthewzeiler.com/" target="_blank">Website</a></li><li><a href="https://www.linkedin.com/in/mattzeiler/" target="_blank">LinkedIn</a></li></ul>Parting Question<br /><ul><li>From your perspective, what is the biggest barrier to adoption of machine learning today?</li></ul>Closing Announcements<br /><ul><li>Thank you for listening! Don't forget to check out our other shows. The <a href="https://www.dataengineeringpodcast.com" target="_blank">Data Engineering Podcast</a> covers the latest on modern data management. [Podcast.__init__]() covers the Python language, its community, and the innovative ways it is being used.</li><li>Visit the <a href="https://www.aiengineeringpodcast.com" target="_blank">site</a> to subscribe to the show, sign up for the mailing list, and read the show notes.</li><li>If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.</li><li>To help other people find the show please leave a review on <a href="https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243" target="_blank">iTunes</a> and tell your friends and co-workers.</li></ul>Links<br /><ul><li><a href="https://www.clarifai.com/" target="_blank">Clarifai</a></li><li><a href="http://www.cs.toronto.edu/~hinton/" target="_blank">Geoff Hinton</a></li><li><a href="https://yann.lecun.com/" target="_blank">Yann Lecun</a></li><li><a href="https://en.wikipedia.org/wiki/Neural_network_(machine_learning)" target="_blank">Neural Networks</a></li><li><a href="https://en.wikipedia.org/wiki/Deep_learning" target="_blank">Deep Learning</a></li><li><a href="https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/" target="_blank">Retrieval Augmented Generation</a></li><li><a href="https://medium.com/@crskilpatrick807/context-windows-the-short-term-memory-of-large-language-models-ab878fc6f9b5" target="_blank">Context Window</a></li><li><a href="https://en.wikipedia.org/wiki/Vector_database" target="_blank">Vector Database</a></li><li><a href="https://www.promptingguide.ai/" target="_blank">Prompt Engineering</a></li><li><a href="https://mistral.ai/" target="_blank">Mistral</a></li><li><a href="https://llama.meta.com/" target="_blank">Llama 3</a></li><li><a href="https://huggingface.co/blog/embedding-quantization" target="_blank">Embedding Quantization</a></li><li><a href="https://en.wikipedia.org/wiki/Active_learning_(machine_learning)" target="_blank">Active Learning</a></li><li><a href="https://deepmind.google/technologies/gemini/" target="_blank">Google Gemini</a></li><li><a href="https://en.wikipedia.org/wiki/Attention_(machine_learning)" target="_blank">AI Model Attention</a></li><li><a href="https://en.wikipedia.org/wiki/Recurrent_neural_network" target="_blank">Recurrent Network</a></li><li><a href="https://en.wikipedia.org/wiki/Convolutional_neural_network" target="_blank">Convolutional Network</a></li><li><a href="https://medium.com/@ashpaklmulani/improve-retrieval-augmented-generation-rag-with-re-ranking-31799c670f8e" target="_blank">Reranking Model</a></li><li><a href="https://en.wikipedia.org/wiki/Stop_word" target="_blank">Stop Words</a></li><li><a href="https://huggingface.co/blog/mteb" target="_blank">Massive Text Embedding Benchmark (MTEB)</a></li><li><a href="https://retool.com/blog/state-of-ai-h1-2024" target="_blank">Retool State of AI Report</a></li><li><a href="https://github.com/pgvector/pgvector" target="_blank">pgvector</a></li><li><a href="https://milvus.io/" target="_blank">Milvus</a></li><li><a href="https://qdrant.tech/" target="_blank">Qdrant</a></li><li><a href="https://www.pinecone.io/" target="_blank">Pinecone</a></li><li><a href="https://huggingface.co/open-llm-leaderboard" target="_blank">OpenLLM Leaderboard</a></li><li><a href="https://en.wikipedia.org/wiki/Semantic_search" target="_blank">Semantic Search</a></li><li><a href="https://www.hashicorp.com/" target="_blank">Hashicorp</a></li></ul>The intro and outro music is from <a href="https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/" target="_blank">Hitman's Lovesong feat. Paola Graziano</a> by <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/" target="_blank">The Freak Fandango Orchestra</a>/<a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">CC BY-SA 3.0</a>
play-circle
63 MIN
Barking Up The Wrong GPTree: Building Better AI With A Cognitive Approach
JUL 28, 2024
Barking Up The Wrong GPTree: Building Better AI With A Cognitive Approach
Summary<br />Artificial intelligence has dominated the headlines for several months due to the successes of large language models. This has prompted numerous debates about the possibility of, and timeline for, artificial general intelligence (AGI). Peter Voss has dedicated decades of his life to the pursuit of truly intelligent software through the approach of cognitive AI. In this episode he explains his approach to building AI in a more human-like fashion and the emphasis on learning rather than statistical prediction.<br /><br />Announcements<br /><ul><li>Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems</li><li>Your host is Tobias Macey and today I'm interviewing Peter Voss about what is involved in making your AI applications more "human"</li></ul>Interview<br /><ul><li>Introduction</li><li>How did you get involved in machine learning?</li><li>Can you start by unpacking the idea of "human-like" AI?</li><li>How does that contrast with the conception of "AGI"?</li><li>The applications and limitations of GPT/LLM models have been dominating the popular conversation around AI. How do you see that impacting the overrall ecosystem of ML/AI applications and investment?</li><li>The fundamental/foundational challenge of every AI use case is sourcing appropriate data. What are the strategies that you have found useful to acquire, evaluate, and prepare data at an appropriate scale to build high quality models?&nbsp;</li><li>What are the opportunities and limitations of causal modeling techniques for generalized AI models?</li><li>As AI systems gain more sophistication there is a challenge with establishing and maintaining trust. What are the risks involved in deploying more human-level AI systems and monitoring their reliability?</li><li>What are the practical/architectural methods necessary to build more cognitive AI systems?</li><li>How would you characterize the ecosystem of tools/frameworks available for creating, evolving, and maintaining these applications?</li><li>What are the most interesting, innovative, or unexpected ways that you have seen cognitive AI applied?</li><li>What are the most interesting, unexpected, or challenging lessons that you have learned while working on desiging/developing cognitive AI systems?</li><li>When is cognitive AI the wrong choice?</li><li>What do you have planned for the future of cognitive AI applications at Aigo?</li></ul>Contact Info<br /><ul><li><a href="https://www.linkedin.com/in/vosspeter/" target="_blank">LinkedIn</a></li><li><a href="http://optimal.org/voss.html" target="_blank">Website</a></li></ul>Parting Question<br /><ul><li>From your perspective, what is the biggest barrier to adoption of machine learning today?</li></ul>Closing Announcements<br /><ul><li>Thank you for listening! Don't forget to check out our other shows. The <a href="https://www.dataengineeringpodcast.com" target="_blank">Data Engineering Podcast</a> covers the latest on modern data management. <a href="https://www.pythonpodcast.com" target="_blank">Podcast.__init__</a> covers the Python language, its community, and the innovative ways it is being used.</li><li>Visit the <a href="https://www.aiengineeringpodcast.com" target="_blank">site</a> to subscribe to the show, sign up for the mailing list, and read the show notes.</li><li>If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.</li><li>To help other people find the show please leave a review on <a href="https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243" target="_blank">iTunes</a> and tell your friends and co-workers.</li></ul>Links<br /><ul><li><a href="https://aigo.ai/" target="_blank">Aigo.ai</a></li><li><a href="https://aigo.ai/what-is-real-agi/" target="_blank">Artificial General Intelligence</a></li><li><a href="https://aigo.ai/cognitive-ai/" target="_blank">Cognitive AI</a></li><li><a href="https://en.wikipedia.org/wiki/Knowledge_graph" target="_blank">Knowledge Graph</a></li><li><a href="https://en.wikipedia.org/wiki/Causal_model" target="_blank">Causal Modeling</a></li><li><a href="https://en.wikipedia.org/wiki/Bayesian_statistics" target="_blank">Bayesian Statistics</a></li><li><a href="https://amzn.to/3UJKsmK" target="_blank">Thinking Fast &amp; Slow</a> by Daniel Kahneman (affiliate link)</li><li><a href="https://en.wikipedia.org/wiki/Agent-based_model" target="_blank">Agent-Based Modeling</a></li><li><a href="https://en.wikipedia.org/wiki/Reinforcement_learning" target="_blank">Reinforcement Learning</a></li><li><a href="https://www.darpa.mil/about-us/darpa-perspective-on-ai" target="_blank">DARPA 3 Waves of AI</a> presentation</li><li><a href="https://arxiv.org/abs/2308.03598" target="_blank">Why Don't We Have AGI Yet?</a> whitepaper</li><li><a href="https://arxiv.org/abs/2309.01622" target="_blank">Concepts Is All You Need</a> Whitepaper</li><li><a href="https://en.wikipedia.org/wiki/Helen_Keller" target="_blank">Hellen Keller</a></li><li><a href="https://en.wikipedia.org/wiki/Stephen_Hawking" target="_blank">Stephen Hawking</a></li></ul>The intro and outro music is from <a href="https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/" target="_blank">Hitman's Lovesong feat. Paola Graziano</a> by <a href="http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/" target="_blank">The Freak Fandango Orchestra</a>/<a href="https://creativecommons.org/licenses/by-sa/3.0/" target="_blank">CC BY-SA 3.0</a>
play-circle
52 MIN