Practical AI

Practical AI Artwork

Making artificial intelligence practical, productive & accessible to everyone

This podcast is not in production. Please browse and enjoy the archive below.

Practical AI Practical AI #230

Cambrian explosion of generative models

Play
2023-07-06T17:30:00Z #ai +3 šŸŽ§ 30,537

In this Fully Connected episode, Daniel and Chris explore recent highlights from the current model proliferation wave sweeping the world - including Stable Diffusion XL, OpenChat, Zeroscope XL, and Salesforce XGen. They note the rapid rise of open models, and speculate that just as in open source software, open models will dominate the future. Such rapid advancement creates its own problems though, so they finish by itemizing concerns such as cybersecurity, workflow productivity, and impact on human culture.

Practical AI Practical AI #242

Deep learning in Rust with Burn šŸ”„

Play
2023-10-24T20:40:00Z #ai +2 šŸŽ§ 30,445

It seems like everyone is interested in Rust these days. Even the most popular Python linter, Ruff, isn’t written in Python! It’s written in Rust. But what is the state of training or inferencing deep learning models in Rust? In this episode, we are joined by Nathaniel Simard, the creator burn. We discuss Rust in general, the need to have support for AI in multiple languages, and the current state of doing ā€œAI thingsā€ in Rust.

Practical AI Practical AI #222

The last mile of AI app development

Play
2023-05-11T13:00:00Z #ai +3 šŸŽ§ 30,443

There are a ton of problems around building LLM apps in production and the last mile of that problem. Travis Fischer, builder of open AI projects like @ChatGPTBot, joins us to talk through these problems (and how to overcome them). He helps us understand the hierarchy of complexity from simple prompting to augmentation, agents, and fine-tuning. Along the way we discuss the frontend developer community that is rapidly adopting AI technology via Typescript (not Python).

Practical AI Practical AI #243

Self-hosting & scaling models

Play
2023-10-31T18:00:00Z #ai +2 šŸŽ§ 30,302

We’re excited to have Tuhin join us on the show once again to talk about self-hosting open access models. Tuhin’s company Baseten specializes in model deployment and monitoring at any scale, and it was a privilege to talk with him about the trends he is seeing in both tooling and usage of open access models. We were able to touch on the common use cases for integrating self-hosted models and how the boom in generative AI has influenced that ecosystem.

Practical AI Practical AI #224

Data augmentation with LlamaIndex

Play
2023-05-23T16:15:00Z #ai +1 šŸŽ§ 30,250

Large Language Models (LLMs) continue to amaze us with their capabilities. However, the utilization of LLMs in production AI applications requires the integration of private data. Join us as we have a captivating conversation with Jerry Liu from LlamaIndex, where he provides valuable insights into the process of data ingestion, indexing, and query specifically tailored for LLM applications. Delving into the topic, we uncover different query patterns and venture beyond the realm of vector databases.

Practical AI Practical AI #270

First impressions of GPT-4o

Play
2024-05-22T00:30:00Z #ai +2 šŸŽ§ 30,217

Daniel & Chris share their first impressions of OpenAI’s newest LLM: GPT-4o and Daniel tries to bring the model into the conversation with humorously mixed results. Together, they explore the implications of Omni’s new feature set - the speed, the voice interface, and the new multimodal capabilities.

Practical AI Practical AI #281

Gaudi processors & Intel's AI portfolio

Play
2024-08-07T13:45:00Z #ai šŸŽ§ 30,077

There is an increasing desire for and effort towards GPU alternatives for AI workloads and an ability to run GenAI models on CPUs. Ben and Greg from Intel join us in this episode to help us understand Intel’s strategy as it related to AI along with related projects, hardware, and developer communities. We dig into Intel’s Gaudi processors, open source collaborations with Hugging Face, and AI on CPU/Xeon processors.

Practical AI Practical AI #216

Explainable AI that is accessible for all humans

Play
2023-03-28T15:30:00Z #ai šŸŽ§ 29,932

We are seeing an explosion of AI apps that are (at their core) a thin UI on top of calls to OpenAI generative models. What risks are associated with this sort of approach to AI integration, and is explainability and accountability something that can be achieved in chat-based assistants?

Beth Rudden of Bast.ai has been thinking about this topic for some time and has developed an ontological approach to creating conversational AI. We hear more about that approach and related work in this episode.

Practical AI Practical AI #289

Understanding what's possible, doable & scalable

Play
2024-10-03T15:45:00Z #ai +1 šŸŽ§ 29,929

We are constantly hearing about disillusionment as it relates to AI. Some of that is probably valid, but Mike Lewis, an AI architect from Cincinnati, has proven that he can consistently get LLM and GenAI apps to the point of real enterprise value (even with the Big Cos of the world). In this episode, Mike joins us to share some stories from the AI trenches & highlight what it takes (practically) to show what is possible, doable & scalable with AI.

Practical AI Practical AI #244

Government regulation of AI has arrived

Play
2023-11-07T14:00:00Z #ai +2 šŸŽ§ 29,907

On Monday, October 30, 2023, the U.S. White House issued its Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Two days later, a policy paper was issued by the U.K. government entitled The Bletchley Declaration by Countries Attending the AI Safety Summit, 1-2 November 2023. It was signed by 29 countries, including the United States and China, the global leaders in AI research.

In this Fully Connected episode, Daniel and Chris parse the details and highlight key takeaways from these documents, especially the extensive and detailed executive order, which has the force of law in the United States.

Practical AI Practical AI #220

Causal inference

Play
2023-04-25T16:35:00Z #ai šŸŽ§ 29,882

With all the LLM hype, it’s worth remembering that enterprise stakeholders want answers to ā€œwhyā€ questions. Enter causal inference. Paul Hünermund has been doing research and writing on this topic for some time and joins us to introduce the topic. He also shares some relevant trends and some tips for getting started with methods including double machine learning, experimentation, difference-in-difference, and more.

Practical AI Practical AI #229

Automated cartography using AI

Play
2023-06-28T14:30:00Z #ai +1 šŸŽ§ 29,716

Your feed might be dominated by LLMs these days, but there are some amazing things happening in computer vision that you shouldn’t ignore! In this episode, we bring you one of those amazing stories from Gabriel Ortiz, who is working with the government of Cantabria in Spain to automate cartography and apply AI to geospatial analysis. We hear about how AI tooling fits into the GIS workflow, and Gabriel shares some of his recent work (including work that can identify individual people, invasive plant species, building and more from aerial survey data).

Practical AI Practical AI #283

Threat modeling LLM apps

Play
2024-08-22T13:30:00Z #ai +2 šŸŽ§ 29,714

If you have questions at the intersection of Cybersecurity and AI, you need to know Donato at WithSecure! Donato has been threat modeling AI applications and seriously applying those models in his day-to-day work. He joins us in this episode to discuss his LLM application security canvas, prompt injections, alignment, and more.

Practical AI Practical AI #250

Open source, on-disk vector search with LanceDB

Play
2023-12-19T19:40:00Z #ai +3 šŸŽ§ 29,657

Prashanth Rao mentioned LanceDB as a stand out amongst the many vector DB options in episode #234. Now, Chang She (co-founder and CEO of LanceDB) joins us to talk through the specifics of their open source, on-disk, embedded vector search offering. We talk about how their unique columnar database structure enables serverless deployments and drastic savings (without performance hits) at scale. This one is super practical, so don’t miss it!

Practical AI Practical AI #231

A developer's toolkit for SOTA AI

Play
2023-07-12T21:00:00Z #ai +2 šŸŽ§ 29,646

Chris sat down with Varun Mohan and Anshul Ramachandran, CEO / Cofounder and Lead of Enterprise and Partnership at Codeium, respectively. They discussed how to streamline and enable modern development in generative AI and large language models (LLMs). Their new tool, Codeium, was born out of the insights they gleaned from their work in GPU software and solutions development, particularly with respect to generative AI, large language models, and supporting infrastructure. Codeium is a free AI-powered toolkit for developers, with in-house models and infrastructure - not another API wrapper.

Practical AI Practical AI #287

Pausing to think about scikit-learn & OpenAI o1

Play
2024-09-17T19:00:00Z #ai +1 šŸŽ§ 29,099

Recently the company stewarding the open source library scikit-learn announced their seed funding. Also, OpenAI released ā€œo1ā€ with new behavior in which it pauses to ā€œthinkā€ about complex tasks. Chris and Daniel take some time to do their own thinking about o1 and the contrast to the scikit-learn ecosystem, which has the goal to promote ā€œdata science that you own.ā€

Practical AI Practical AI #276

Stanford's AI Index Report 2024

Play
2024-07-02T19:45:00Z #ai šŸŽ§ 28,769

We’ve had representatives from Stanford’s Institute for Human-Centered Artificial Intelligence (HAI) on the show in the past, but we were super excited to talk through their 2024 AI Index Report after such a crazy year in AI! Nestor from HAI joins us in this episode to talk about some of the main takeaways including how AI makes workers more productive, the US is increasing regulations sharply, and industry continues to dominate frontier AI research.

Practical AI Practical AI #225

Controlled and compliant AI applications

Play
2023-05-31T17:00:00Z #ai +2 šŸŽ§ 28,666

You can’t build robust systems with inconsistent, unstructured text output from LLMs. Moreover, LLM integrations scare corporate lawyers, finance departments, and security professionals due to hallucinations, cost, lack of compliance (e.g., HIPAA), leaked IP/PII, and ā€œinjectionā€ vulnerabilities.

In this episode, Chris interviews Daniel about his new company called Prediction Guard, which addresses these issues. They discuss some practical methodologies for getting consistent, structured output from compliant AI systems. These systems, driven by open access models and various kinds of LLM wrappers, can help you delight customers AND navigate the increasing restrictions on ā€œGPTā€ models.

Practical AI Practical AI #296

scikit-learn & data science you own

Play
2024-11-19T21:00:00Z #ai +1 šŸŽ§ 28,566

We are at GenAI saturation, so let’s talk about scikit-learn, a long time favorite for data scientists building classifiers, time series analyzers, dimensionality reducers, and more! Scikit-learn is deployed across industry and driving a significant portion of the ā€œAIā€ that is actually in production. :probabl is a new kind of company that is stewarding this project along with a variety of other open source projects. Yann Lechelle and Guillaume Lemaitre share some of the vision behind the company and talk about the future of scikit-learn!

Practical AI Practical AI #295

Creating tested, reliable AI applications

Play
2024-11-13T19:30:00Z #ai šŸŽ§ 28,468

It can be frustrating to get an AI application working amazingly well 80% of the time and failing miserably the other 20%. How can you close the gap and create something that you rely on? Chris and Daniel talk through this process, behavior testing, and the flow from prototype to production in this episode. They also talk a bit about the apparent slow down in the release of frontier models.

Practical AI Practical AI #254

Large Action Models (LAMs) & Rabbits šŸ‡

Play
2024-01-30T21:00:00Z #ai +2 šŸŽ§ 28,438

Recently the release of the rabbit r1 device resulted in huge interest in both the device and ā€œLarge Action Modelsā€ (or LAMs). What is an LAM? Is this something new? Did these models come out of nowhere, or are they related to other things we are already using? Chris and Daniel dig into LAMs in this episode and discuss neuro-symbolic AI, AI tool usage, multimodal models, and more.

Practical AI Practical AI #223

Creating instruction tuned models

Play
2023-05-16T18:20:00Z #ai +1 šŸŽ§ 28,396

At the recent ODSC East conference, Daniel got a chance to sit down with Erin Mikail Staples to discuss the process of gathering human feedback and creating an instruction tuned Large Language Models (LLM). They also chatted about the importance of open data and practical tooling for data annotation and fine-tuning. Do you want to create your own custom generative AI models? This is the episode for you!

Practical AI Practical AI #226

Accidentally building SOTA AI

Play
2023-06-06T20:45:00Z #ai +2 šŸŽ§ 28,345

Lately.AI has been working for years on content generation systems that capture your unique ā€œvoiceā€ and are tailored to your unique audience. At first, they didn’t know that they were going to build an AI system, but now they have a state-of-the-art generative platform that provides much more than ā€œpromptingā€ out of thin air. Lately.AI’s CEO Kate explain their journey, her perspective on generative AI in marketing, and much more in this episode!

Practical AI Practical AI #290

Towards high-quality (maybe synthetic) datasets

Play
2024-10-09T13:30:00Z #ai +1 šŸŽ§ 28,244

As Argilla puts it: ā€œData quality is what makes or breaks AI.ā€ However, what exactly does this mean and how can AI team probably collaborate with domain experts towards improved data quality? David Berenstein & Ben Burtenshaw, who are building Argilla & Distilabel at Hugging Face, join us to dig into these topics along with synthetic data generation & AI-generated labeling / feedback.

Practical AI Practical AI #269

Full-stack approach for effective AI agents

Play
2024-05-15T14:00:00Z #ai šŸŽ§ 28,206

There’s a lot of hype about AI agents right now, but developing robust agents isn’t yet a reality in general. Imbue is leading the way towards more robust agents by taking a full-stack approach; from hardware innovations through to user interface. In this episode, Josh, Imbue’s CTO, tell us more about their approach and some of what they have learned along the way.

Player art
  0:00 / 0:00