Practical AI
Episodes
Large Action Models (LAMs) & Rabbits 🐇
30 Jan 2024
Contributed by Lukas
Recently the release of the rabbit r1 device resulted in huge interest in both the device and “Large Action Models” (or LAMs). What is an LAM? Is ...
Collaboration & evaluation for LLM apps
23 Jan 2024
Contributed by Lukas
Small changes in prompts can create large changes in the output behavior of generative AI models. Add to that the confusion around proper evaluation o...
Advent of GenAI Hackathon recap
17 Jan 2024
Contributed by Lukas
Recently, Intel’s Liftoff program for startups and Prediction Guard hosted the first ever “Advent of GenAI” hackathon. 2,000 people from all aro...
AI predictions for 2024
10 Jan 2024
Contributed by Lukas
We scoured the internet to find all the AI related predictions for 2024 (at least from people that might know what they are talking about), and, in th...
Open source, on-disk vector search with LanceDB
19 Dec 2023
Contributed by Lukas
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) join...
The state of open source AI
12 Dec 2023
Contributed by Lukas
The new open source AI book from PremAI starts with “As a data scientist/ML engineer/developer with a 9 to 5 job, it’s difficult to keep track of ...
Suspicion machines ⚙️
05 Dec 2023
Contributed by Lukas
In this enlightening episode, we delve deeper than the usual buzz surrounding AI’s perils, focusing instead on the tangible problems emerging from t...
The OpenAI debacle (a retrospective)
29 Nov 2023
Contributed by Lukas
Daniel & Chris conduct a retrospective analysis of the recent OpenAI debacle in which CEO Sam Altman was sacked by the OpenAI board, only to retur...
Generating product imagery at Shopify
21 Nov 2023
Contributed by Lukas
Shopify recently released a Hugging Face space demonstrating very impressive results for replacing background scenes in product imagery. In this episo...
AI trailblazers putting people first
14 Nov 2023
Contributed by Lukas
According to Solana Larsen: “Too often, it feels like we have lost control of the internet to the interests of Big Tech, Big Data — and now Big AI...
Government regulation of AI has arrived
07 Nov 2023
Contributed by Lukas
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 In...
Self-hosting & scaling models
31 Oct 2023
Contributed by Lukas
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 m...
Deep learning in Rust with Burn 🔥
24 Oct 2023
Contributed by Lukas
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....
AI's impact on developers
20 Oct 2023
Contributed by Lukas
Chris & Daniel are out this week, so we’re bringing you a panel discussion from All Things Open 2023 moderated by Jerod Santo (Practical AI prod...
Generative models: exploration to deployment
03 Oct 2023
Contributed by Lukas
What is the model lifecycle like for experimenting with and then deploying generative AI models? Although there are some similarities, this lifecycle ...
Automate all the UIs!
20 Sep 2023
Contributed by Lukas
Dominik Klotz from askui joins Daniel and Chris to discuss the automation of UI, and how AI empowers them to automate any use case on any operating sy...
Fine-tuning vs RAG
06 Sep 2023
Contributed by Lukas
In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along th...
Automating code optimization with LLMs
29 Aug 2023
Contributed by Lukas
You might have heard a lot about code generation tools using AI, but could LLMs and generative AI make our existing code better? In this episode, we s...
The new AI app stack
23 Aug 2023
Contributed by Lukas
Recently a16z released a diagram showing the “Emerging Architectures for LLM Applications.” In this episode, we expand on things covered in that d...
Blueprint for an AI Bill of Rights
09 Aug 2023
Contributed by Lukas
In this Fully Connected episode, Daniel and Chris kick it off by noting that Stability AI released their SDXL 1.0 LLM! They discuss its virtues, and t...
Vector databases (beyond the hype)
01 Aug 2023
Contributed by Lukas
There’s so much talk (and hype) these days about vector databases. We thought it would be timely and practical to have someone on the show that has ...
There's a new Llama in town
25 Jul 2023
Contributed by Lukas
It was an amazing week in AI news. Among other things, there is a new NeRF and a new Llama in town!!! Zip-NeRF can create some amazing 3D scenes based...
Legal consequences of generated content
18 Jul 2023
Contributed by Lukas
As a technologist, coder, and lawyer, few people are better equipped to discuss the legal and practical consequences of generative AI than Damien Rieh...
A developer's toolkit for SOTA AI
12 Jul 2023
Contributed by Lukas
Chris sat down with Varun Mohan and Anshul Ramachandran, CEO / Cofounder and Lead of Enterprise and Partnership at Codeium, respectively. They discuss...
Cambrian explosion of generative models
06 Jul 2023
Contributed by Lukas
In this Fully Connected episode, Daniel and Chris explore recent highlights from the current model proliferation wave sweeping the world - including S...
Automated cartography using AI
28 Jun 2023
Contributed by Lukas
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 e...
From ML to AI to Generative AI
21 Jun 2023
Contributed by Lukas
Chris and Daniel take a step back to look at how generative AI fits into the wider landscape of ML/AI and data science. They talk through the differen...
AI trends: a Latent Space crossover
14 Jun 2023
Contributed by Lukas
Daniel had the chance to sit down with @swyx and Alessio from the Latent Space pod in SF to talk about current AI trends and to highlight some key lea...
Accidentally building SOTA AI
06 Jun 2023
Contributed by Lukas
Lately.AI has been working for years on content generation systems that capture your unique “voice” and are tailored to your unique audience. At f...
Controlled and compliant AI applications
31 May 2023
Contributed by Lukas
You can’t build robust systems with inconsistent, unstructured text output from LLMs. Moreover, LLM integrations scare corporate lawyers, finance de...
Data augmentation with LlamaIndex
23 May 2023
Contributed by Lukas
Large Language Models (LLMs) continue to amaze us with their capabilities. However, the utilization of LLMs in production AI applications requires the...
Creating instruction tuned models
16 May 2023
Contributed by Lukas
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 cr...
The last mile of AI app development
11 May 2023
Contributed by Lukas
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...
Large models on CPUs
02 May 2023
Contributed by Lukas
Model sizes are crazy these days with billions and billions of parameters. As Mark Kurtz explains in this episode, this makes inference slow and expen...
Causal inference
25 Apr 2023
Contributed by Lukas
With all the LLM hype, it’s worth remembering that enterprise stakeholders want answers to “why” questions. Enter causal inference. Paul Hünerm...
Capabilities of LLMs 🤯
19 Apr 2023
Contributed by Lukas
Large Language Model (LLM) capabilities have reached new heights and are nothing short of mind-blowing! However, with so many advancements happening a...
Computer scientists as rogue art historians
12 Apr 2023
Contributed by Lukas
What can art historians and computer scientists learn from one another? Actually, a lot! Amanda Wasielewski joins us to talk about how she discovered ...
Accelerated data science with a Kaggle grandmaster
04 Apr 2023
Contributed by Lukas
Daniel and Chris explore the intersection of Kaggle and real-world data science in this illuminating conversation with Christof Henkel, Senior Deep Le...
Explainable AI that is accessible for all humans
28 Mar 2023
Contributed by Lukas
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 t...
AI search at You.com
15 Mar 2023
Contributed by Lukas
Neural search and chat-based search are all the rage right now. However, You.com has been innovating in these topics long before ChatGPT. In this epis...
End-to-end cloud compute for AI/ML
07 Mar 2023
Contributed by Lukas
We’ve all experienced pain moving from local development, to testing, and then on to production. This cycle can be long and tedious, especially as A...
Success (and failure) in prompting
28 Feb 2023
Contributed by Lukas
With the recent proliferation of generative AI models (from OpenAI, co:here, Anthropic, etc.), practitioners are racing to come up with best practices...
Applied NLP solutions & AI education
22 Feb 2023
Contributed by Lukas
We’re super excited to welcome Jay Alammar to the show. Jay is a well-known AI educator, applied NLP practitioner at co:here, and author of the popu...
Serverless GPUs
14 Feb 2023
Contributed by Lukas
We’ve been hearing about “serverless” CPUs for some time, but it’s taken a while to get to serverless GPUs. In this episode, Erik from Banana ...
MLOps is alive and well
07 Feb 2023
Contributed by Lukas
Worlds are colliding! This week we join forces with the hosts of the MLOps.Community podcast to discuss all things machine learning operations. We tal...
3D assets & simulation at NVIDIA
31 Jan 2023
Contributed by Lukas
What’s the current reality and practical implications of using 3D environments for simulation and synthetic data creation? In this episode, we cut r...
GPU dev environments that just work
24 Jan 2023
Contributed by Lukas
Creating and sharing reproducible development environments for AI experiments and production systems is a huge pain. You have all sorts of weird depen...
Machine learning at small organizations
17 Jan 2023
Contributed by Lukas
Why is ML is so poorly adopted in small organizations (hint: it’s not because they don’t have enough data)? In this episode, Kirsten Lum from Stor...
ChatGPT goes prime time!
10 Jan 2023
Contributed by Lukas
Daniel and Chris do a deep dive into OpenAI’s ChatGPT, which is the first LLM to enjoy direct mass adoption by folks outside the AI world. They disc...
NLP research by & for local communities
03 Jan 2023
Contributed by Lukas
While at EMNLP 2022, Daniel got a chance to sit down with an amazing group of researchers creating NLP technology that actually works for their local ...
SOTA machine translation at Unbabel
13 Dec 2022
Contributed by Lukas
José and Ricardo joined Daniel at EMNLP 2022 to discuss state-of-the-art machine translation, the WMT shared tasks, and quality estimation. Among oth...
AI competitions & cloud resources
07 Dec 2022
Contributed by Lukas
In this special episode, we interview some of the sponsors and teams from a recent case competition organized by Purdue University, Microsoft, INFORMS...
Copilot lawsuits & Galactica "science"
29 Nov 2022
Contributed by Lukas
There are some big AI-related controversies swirling, and it’s time we talk about them. A lawsuit has been filed against GitHub, Microsoft, and Open...
Protecting us with the Database of Evil
16 Nov 2022
Contributed by Lukas
Online platforms and their users are susceptible to a barrage of threats – from disinformation to extremism to terror. Daniel and Chris chat with Ma...
Hybrid computing with quantum processors
08 Nov 2022
Contributed by Lukas
It’s been a while since we’ve touched on quantum computing. It’s time for an update! This week we talk with Yonatan from Quantum Machines about ...
The practicalities of releasing models
01 Nov 2022
Contributed by Lukas
Recently Chris and Daniel briefly discussed the Open RAIL-M licensing and model releases on Hugging Face. In this episode, Daniel follows up on this t...
AI adoption in large, well-established companies
26 Oct 2022
Contributed by Lukas
This panel discussion was recorded at a recent event hosted by a company, Aryballe, that we previously featured on the podcast (#120). We got a chance...
Data for All
18 Oct 2022
Contributed by Lukas
People are starting to wake up to the fact that they have control and ownership over their data, and governments are moving quickly to legislate these...
What's up, DocQuery?
12 Oct 2022
Contributed by Lukas
Chris sits down with Ankur Goyal to talk about DocQuery, Impira’s new open source ML model. DocQuery lets you ask questions about semi-structured da...
Production data labeling workflows
27 Sep 2022
Contributed by Lukas
It’s one thing to gather some labels for your data. It’s another thing to integrate data labeling into your workflows and infrastructure in a scal...
Evaluating models without test data
20 Sep 2022
Contributed by Lukas
WeightWatcher, created by Charles Martin, is an open source diagnostic tool for analyzing Neural Networks without training or even test data! Charles ...
Stable Diffusion
13 Sep 2022
Contributed by Lukas
The new stable diffusion model is everywhere! Of course you can use this model to quickly and easily create amazing, dream-like images to post on twit...
Licensing & automating creativity
06 Sep 2022
Contributed by Lukas
AI is increasingly being applied in creative and artistic ways, especially with recent tools integrating models like Stable Diffusion. This is making ...
Privacy in the age of AI
30 Aug 2022
Contributed by Lukas
In this Fully-Connected episode, Daniel and Chris discuss concerns of privacy in the face of ever-improving AI / ML technologies. Evaluating AI’s im...
Practical, positive uses for deep fakes
24 Aug 2022
Contributed by Lukas
Differentiating between what is real versus what is fake on the internet can be challenging. Historically, AI deepfakes have only added to the confusi...
CMU's AI pilot lands in the news 🗞
16 Aug 2022
Contributed by Lukas
Daniel and Chris cover the AI news of the day in this wide-ranging discussion. They start with Truss from Baseten while addressing how to categorize A...
AlphaFold is revolutionizing biology
09 Aug 2022
Contributed by Lukas
AlphaFold is an AI system developed by DeepMind that predicts a protein’s 3D structure from its amino acid sequence. It regularly achieves accuracy ...
AI IRL & Mozilla's Internet Health Report
02 Aug 2022
Contributed by Lukas
Every year Mozilla releases an Internet Health Report that combines research and stories exploring what it means for the internet to be healthy. This ...
The geopolitics of artificial intelligence
26 Jul 2022
Contributed by Lukas
In this Fully-Connected episode, Chris and Daniel explore the geopolitics, economics, and power-brokering of artificial intelligence. What does contro...
DALL-E is one giant leap for raccoons! 🔭
19 Jul 2022
Contributed by Lukas
In this Fully-Connected episode, Daniel and Chris explore DALL-E 2, the amazing new model from Open AI that generates incredibly detailed novel images...
Cloning voices with Coqui
12 Jul 2022
Contributed by Lukas
Coqui is a speech technology startup that making huge waves in terms of their contributions to open source speech technology, open access models and d...
AI's role in reprogramming immunity
28 Jun 2022
Contributed by Lukas
Drausin Wulsin, Director of ML at Immunai, joins Daniel & Chris to talk about the role of AI in immunotherapy, and why it is proving to be the for...
Machine learning in your database
22 Jun 2022
Contributed by Lukas
While scaling up machine learning at Instacart, Montana Low and Lev Kokotov discovered just how much you can do with the Postgres database. They are b...
Digital humans & detecting emotions
14 Jun 2022
Contributed by Lukas
Could we create a digital human that processes data in a variety of modalities and detects emotions? Well, that’s exactly what NTT DATA Services is ...
Generalist models & Iceman's voice
07 Jun 2022
Contributed by Lukas
In this “fully connected” episode of the podcast, we catch up on some recent developments in the AI world, including a new model from DeepMind cal...
🤗 The AI community building the future
31 May 2022
Contributed by Lukas
Hugging Face is increasingly becomes the “hub” of AI innovation. In this episode, Merve Noyan joins us to dive into this hub in more detail. We di...
Active learning & endangered languages
17 May 2022
Contributed by Lukas
Don’t all AI methods need a bunch of data to work? How could AI help document and revitalize endangered languages with “human-in-the-loop” or “...
Learning the language of life
03 May 2022
Contributed by Lukas
AI is discovering new drugs. Sound like science fiction? Not at Absci! Sean and Joshua join us to discuss their AI-driven pipeline for drug discovery....
MLOps is NOT Real
26 Apr 2022
Contributed by Lukas
We all hear a lot about MLOps these days, but where does MLOps end and DevOps begin? Our friend Luis from OctoML joins us in this episode to discuss t...
🌍 AI in Africa - Agriculture
19 Apr 2022
Contributed by Lukas
In the fourth “AI in Africa” spotlight episode, we welcome Leonida Mutuku and Godliver Owomugisha, two experts in applying advanced technology in ...
Quick, beautiful web UIs for ML apps
05 Apr 2022
Contributed by Lukas
Abubakar Abid joins Daniel and Chris for a tour of Gradio and tells them about the project joining Hugging Face. What’s Gradio? The fastest way to d...
It's been a BIG week in AI news 🗞
29 Mar 2022
Contributed by Lukas
This last week has been a big week for AI news. BigScience is training a huge language model (while the world watches), and NVIDIA announced their lat...
"Foundation" models
23 Mar 2022
Contributed by Lukas
The term “foundation” model has been around since about the middle of last year when a research group at Stanford published the comprehensive repo...
Clothing AI in a data fabric
16 Mar 2022
Contributed by Lukas
What happens when your data operations grow to Internet-scale? How do thousands or millions of data producers and consumers efficiently, effectively, ...
Creating a culture of innovation
08 Mar 2022
Contributed by Lukas
Daniel and Chris talk with Lukas Egger, Head of Innovation Office and Strategic Projects at SAP Business Process Intelligence. Lukas describes what it...
Deploying models (to tractors 🚜)
01 Mar 2022
Contributed by Lukas
Alon from Greeneye and Moses from ClearML blew us away when they said that they are training 1000’s of models a year that get deployed to Kubernetes...
One algorithm to rule them all?
15 Feb 2022
Contributed by Lukas
From MIT researchers who have an AI system that rapidly predicts how two proteins will attach, to Facebook’s first high-performance self-supervised ...
🌍 AI in Africa - Voice & language tools
09 Feb 2022
Contributed by Lukas
In the third of the “AI in Africa” spotlight episodes, we welcome Kathleen Siminyu, who is building Kiswahili voice tools at Mozilla. We had a gre...
Exploring deep reinforcement learning
01 Feb 2022
Contributed by Lukas
In addition to being a Developer Advocate at Hugging Face, Thomas Simonini is building next-gen AI in games that can talk and have smart interactions ...
The world needs an AI superhero
25 Jan 2022
Contributed by Lukas
From drug discovery at the Quebec AI Institute to improving capabilities with low-resourced languages at the Masakhane Research Foundation and Google ...
Democratizing ML for speech
19 Jan 2022
Contributed by Lukas
You might know about MLPerf, a benchmark from MLCommons that measures how fast systems can train models to a target quality metric. However, MLCommons...
Eliminate AI failures
11 Jan 2022
Contributed by Lukas
We have all seen how AI models fail, sometimes in spectacular ways. Yaron Singer joins us in this episode to discuss model vulnerabilities and automat...
🌍 AI in Africa - Radiant Earth
05 Jan 2022
Contributed by Lukas
In the second of the “AI in Africa” spotlight episodes, we welcome guests from Radiant Earth to talk about machine learning for earth observation....
OpenAI and Hugging Face tooling
14 Dec 2021
Contributed by Lukas
The time has come! OpenAI’s API is now available with no waitlist. Chris and Daniel dig into the API and playground during this episode, and they al...
Friendly federated learning 🌼
07 Dec 2021
Contributed by Lukas
This episode is a follow up to our recent Fully Connected show discussing federated learning. In that previous discussion, we mentioned Flower (a “f...
Technology as a force for good
02 Dec 2021
Contributed by Lukas
Here’s a bonus episode this week from our friends behind Me, Myself, and AI — a podcast on artificial intelligence and business, and produced by M...
AI-generated code with OpenAI Codex
30 Nov 2021
Contributed by Lukas
Recently, GitHub released Copilot, which is an amazing AI pair programmer powered by OpenAI’s Codex model. In this episode, Natalie Pistunovich tell...
Zero-shot multitask learning
24 Nov 2021
Contributed by Lukas
In this Fully-Connected episode, Daniel and Chris ponder whether in-person AI conferences are on the verge of making a post-pandemic comeback. Then on...
Analyzing the 2021 AI Index Report
10 Nov 2021
Contributed by Lukas
Each year we discuss the latest insights from the Stanford Institute for Human-Centered Artificial Intelligence (HAI), and this year is no different. ...
Photonic computing for AI acceleration
02 Nov 2021
Contributed by Lukas
There are a lot of people trying to innovate in the area of specialized AI hardware, but most of them are doing it with traditional transistors. Light...