AI vs software devs
Daniel and Chris are out this week, so we’re bringing you conversations all about AI’s complicated relationship to software developers from other Changelog pods: JS Party, Go Time & The Changelog.
Subscribe to be notified about new episodes of Practical AI!
Daniel and Chris are out this week, so we’re bringing you conversations all about AI’s complicated relationship to software developers from other Changelog pods: JS Party, Go Time & The Changelog.
Daniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next.
Runway is an applied AI research company shaping the next era of art, entertainment & human creativity. Chris sat down with Runway co-founder / CTO, Anastasis Germanidis, to discuss their rise and how it’s defining the future of the creative landscape with its text & image to video models. We hope you find Anastasis’s founder story as inspiring as Chris did.
While everyone is super hyped about generative AI, computer vision researchers have been working in the background on significant advancements in deep learning architectures. YOLOv9 was just released with some noteworthy advancements relevant to parameter efficient models. In this episode, Chris and Daniel dig into the details and also discuss advancements in parameter efficient LLMs, such as Microsofts 1-Bit LLMs and Qualcomm’s new AI Hub.
Recently, we briefly mentioned the concept of “Activation Hacking” in the episode with Karan from Nous Research. In this fully connected episode, Chris and Daniel dive into the details of this model control mechanism, also called “representation engineering”. Of course, they also take time to discuss the new Sora model from OpenAI.
Chris & Daniel explore AI in national security with Lt. General Jack Shanahan (USAF, Ret.). The conversation reflects Jack’s unique background as the only senior U.S. military officer responsible for standing up and leading two organizations in the United States Department of Defense (DoD) dedicated to fielding artificial intelligence capabilities: Project Maven and the DoD Joint AI Center (JAIC).
Together, Jack, Daniel & Chris dive into the fascinating details of Jack’s recent written testimony to the U.S. Senate’s AI Insight Forum on National Security, in which he provides the U.S. government with thoughtful guidance on how to achieve the best path forward with artificial intelligence.
Google has been releasing a ton of new GenAI functionality under the name “Gemini”, and they’ve officially rebranded Bard as Gemini. We take some time to talk through Gemini compared with offerings from OpenAI, Anthropic, Cohere, etc.
We also discuss the recent FCC decision to ban the use of AI voices in robocalls and what the decision might mean for government involvement in AI in 2024.
Nous Research has been pumping out some of the best open access LLMs using SOTA data synthesis techniques. Their Hermes family of models is incredibly popular! In this episode, Karan from Nous talks about the origins of Nous as a distributed collective of LLM researchers. We also get into fine-tuning strategies and why data synthesis works so well.
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 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.
Small changes in prompts can create large changes in the output behavior of generative AI models. Add to that the confusion around proper evaluation of LLM applications, and you have a recipe for confusion and frustration. Raza and the Humanloop team have been diving into these problems, and, in this episode, Raza helps us understand how non-technical prompt engineers can productively collaborate with technical software engineers while building AI-driven apps.
Recently, Intel’s Liftoff program for startups and Prediction Guard hosted the first ever “Advent of GenAI” hackathon. 2,000 people from all around the world participated in Generate AI related challenges over 7 days. In this episode, we discuss the hackathon, some of the creative solutions, the idea behind it, and more.
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 this episode, we talk about some of the common themes. We also take a moment to look back at 2023 commenting with some distance on a crazy AI year.
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!
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 all the innovations.” We couldn’t agree more, and we are so happy that this week’s guest Casper (among other contributors) have created this resource for practitioners.
During the episode, we cover the key categories to think about as you try to navigate the open source AI ecosystem, and Casper gives his thoughts on fine-tuning, vector DBs & more.
In this enlightening episode, we delve deeper than the usual buzz surrounding AI’s perils, focusing instead on the tangible problems emerging from the use of machine learning algorithms across Europe. We explore “suspicion machines” — systems that assign scores to welfare program participants, estimating their likelihood of committing fraud. Join us as Justin and Gabriel share insights from their thorough investigation, which involved gaining access to one of these models and meticulously analyzing its behavior.
Daniel & Chris conduct a retrospective analysis of the recent OpenAI debacle in which CEO Sam Altman was sacked by the OpenAI board, only to return days later with a new supportive board. The events and people involved are discussed from start to finish along with the potential impact of these events on the AI industry.
Shopify recently released a Hugging Face space demonstrating very impressive results for replacing background scenes in product imagery. In this episode, we hear the backstory technical details about this work from Shopify’s Russ Maschmeyer. Along the way we discuss how to come up with clever AI solutions (without training your own model).
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.” In the latest season of Mozilla’s IRL podcast (edited by Solana), a number of stories are featured to highlight the trailblazers who are reclaiming power over AI to put people first. We discuss some of those stories along with the issues that they surface.
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.
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.
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 “AI things” in Rust.
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 producer and co-host of The Changelog) and featuring keynoters Emily Freeman and James Q Quick.
What is the model lifecycle like for experimenting with and then deploying generative AI models? Although there are some similarities, this lifecycle differs somewhat from previous data science practices in that models are typically not trained from scratch (or even fine-tuned). Chris and Daniel give a high level overview in this effort and discuss model optimization and serving.
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 system. Along the way, the trio explore various approaches and the integration of generative AI, large language models, and computer vision.
In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along the way, we also chat about OpenAI Enterprise, results from the MLOps Community LLM survey, and the orchestration and evaluation of generative AI workloads.
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 sit down with Mike from TurinTech to hear about practical code optimizations using AI “translation” of slow to fast code. We learn about their process for accomplishing this task along with impressive results when automated code optimization is run on existing open source projects.
Recently a16z released a diagram showing the “Emerging Architectures for LLM Applications.” In this episode, we expand on things covered in that diagram to a more general mental model for the new AI app stack. We cover a variety of things from model “middleware” for caching and control to app orchestration.
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 then dive into a discussion regarding how the United States, European Union, and other entities are approaching governance of AI through new laws and legal frameworks. In particular, they review the White House’s approach, noting the potential for unexpected consequences.
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 been hands on with the various options and actually tried to build applications leveraging vector search. Prashanth Rao is a real practitioner that has spent and huge amount of time exploring the expanding set of vector database offerings. After introducing vector database and giving us a mental model of how they fit in with other datastores, Prashanth digs into the trade offs as related to indices, hosting options, embedding vs. query optimization, and more.
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 on 2D images, and Llama 2 from Meta promises to change the LLM landscape. Chris and Daniel dive into these and they compare some of the recently released OpenAI functionality to Anthropic’s Claude 2.