Today’s guest is Logan Kilpatrick, a senior product manager at Google, who tells Ben about his journey from software engineering to machine learning to product management, all with an emphasis on reducing developer friction. They talk through the challenges of non-determinism in AI models and how Google is addressing these issues with a new feature: Grounding with Google Search. Plus, what working at the Apple Store taught Logan about product management.

Eira May

Tom Occhino, now Chief Product Officer at Vercel, tells Ben about how he contributed to the development of React at Facebook and the contentious decision to make React open-source. They also talk about what community feedback has been like on Next.js 15, Vercel’s GenAI web development tool, and how Vercel is rethinking IDEs.

Eira May

Here's a (brief) summary of language model finetuning, the various approaches that exist, their purposes, and what we know about how they work.

Cameron R. Wolfe, PhD

Ben welcomes Ricky Robinett, VP of Developer Relations and Community at Cloudflare, and his eight-year-old daughter Fay for a chat about how AI tools are helping new developers get started and how to encourage your kids to try coding.

Eira May

Ben chats with Shayne Longpre and Robert Mahari of the Data Provenance Initiative about what GenAI means for the data commons. They discuss the decline of public datasets, the complexities of fair use in AI training, the challenges researchers face in accessing data, potential applications for synthetic data, and the evolving legal landscape surrounding AI and copyright.

Eira May

Ben welcomes Sonar CEO Tariq Shaukat for a conversation about AI coding tools’ potential to boost developer productivity—and how to balance those potential gains against code quality and security concerns. They talk about Sonar’s origins as an open-source code quality tool, the excellent reasons to embrace a “clean as you code” philosophy, and how to determine where AI coding tools can be helpful and where they can’t (yet).

Eira May

Ben Popper chats with Keith Babo, Head of Product at Solo.io, about how the API security landscape is changing in the era of GenAI. They talk through the role of governance in AI, the importance of data protection, and the role API gateways play in enhancing security and functionality. Keith shares his insights on retrieval-augmented generation (RAG) systems, protecting PII, and the necessity of human-in-the-loop AI development.

Eira May

There are worries that GenAI systems may run out of fresh data as they scale. Synthetic data is an option, but using AI-generated data to train AI can degrade the model's performance. There may be a better solution. Can data quality overcome a loss of data quantity?

Ben Popper

Ben Popper interviews Vladislav Voroninski, CEO of Helm.ai, about unsupervised learning and the future of AI in autonomous driving. They discuss GenAI’s role in bridging the gap between simulation and reality, the challenges of scaling autonomous driving systems, the commercial potential of partial autonomy, and why software is emerging as a key differentiator in vehicle sales. Vlad spotlights the value of multimodal foundation models and how compute shortages affect AI startups.

Eira May

Socially responsible use of community data needs to be mutually beneficial: the more potential partners are willing to contribute to community development, the more access to community content they receive.

Ellen Brandenberger, Ryan Polk

The entire AI ecosystem is at risk without trust.

Ellen Brandenberger, Ryan Polk

The internet is changing once again: it is becoming more fragmented as the separation between sources of knowledge and how users interact with that knowledge grows.

Ellen Brandenberger, Ryan Polk

If you’re weary of reading about the latest chatbot innovations and the nine ways AI will change your daily life next year, this series of posts may be for you.

Ellen Brandenberger, Ryan Polk

Masked self-attention is the key building block that allows LLMs to learn rich relationships and patterns between the words of a sentence. Let’s build it together from scratch.

Cameron R. Wolfe, PhD

How are developers actually using GenAI-powered coding tools now that some of the initial hype has faded?

Eira May

Founder and entrepreneur Jyoti Bansal tells Ben, Cassidy, and Eira about the developer challenges he aims to solve with his new venture, Harness, an AI-driven software development platform meant to take the pain out of DevOps. Jyoti shares his journey as a founder, his perspective on the venture capital landscape, and his reasons behind his decision to raise debt capital for Harness.

Eira May

Ben chats with Gias Uddin, an assistant professor at York University in Toronto, where he teaches software engineering, data science, and machine learning. His research focuses on designing intelligent tools for testing, debugging, and summarizing software and AI systems. He recently published a paper about detecting errors in code generated by LLMs. Gias and Ben discuss the concept of hallucinations in AI-generated code, the need for tools to detect and correct those hallucinations, and the potential for AI-powered tools to generate QA tests.

Eira May

Ryan chats with Russ d’Sa, cofounder and CEO of LiveKit, about multimodal AI and the technology that makes it possible. They talk through the tech stack required, including the use of WebRTC and UDP protocols for real-time audio and video streaming. They also explore the big challenges involved in ensuring privacy and security in streaming data, namely end-to-end encryption and obfuscation.

Eira May

Ben and Ryan talk to Scott McCarty, Global Senior Principal Product Manager for Red Hat Enterprise Linux, about the intersection between LLMs (large language models) and open source. They discuss the challenges and benefits of open-source LLMs, the importance of attribution and transparency, and the revolutionary potential for LLM-driven applications. They also explore the role of LLMs in code generation, testing, and documentation.

Eira May

More code isn't always a good thing, but fewer bugs is.

Ben Popper

The decoder-only transformer architecture is one of the most fundamental ideas in AI research.

Cameron R. Wolfe, PhD

Ben and Ryan are joined by Robin Gupta for a conversation about benchmarking and testing AI systems. They talk through the lack of trust and confidence in AI, the inherent challenges of nondeterministic systems, the role of human verification, and whether we can (or should) expect an AI to be reliable.

Eira May

Product manager Ash Zade joins the home team to talk about the journey to OverflowAI, a GenAI-powered add-on for Stack Overflow for Teams that’s available now. Ash describes how his team built Enhanced Search, the problems they set out to solve, how they ensured data quality and accuracy, the role of metadata and prompt engineering, and the feedback they’ve gotten from users so far.

Eira May

Ben and Ryan explore why configuration is so complicated, the right to repair, the best programming languages for beginners, how AI is grading exams in Texas, Automattic’s $125M acquisition of Beeper, and why a major US city’s train system still relies on floppy disks. Plus: The unique challenge of keeping up with a field that’s changing as rapidly as GenAI.

Eira May