Reliability for unreliable LLMs
Large language models are non-deterministic by design. Here's how you can inject a little bit of determinism into GenAI workflows.

Large language models are non-deterministic by design. Here's how you can inject a little bit of determinism into GenAI workflows.
Ryan is joined by Tobiko Data co-founders Toby Mao and Iaroslav Zeigerman to talk about the crucial role of rigorous data practices and tooling, the innovations of Tobiko Data’s SQLMesh and SQLGlot, and their insights into the future of data engineering with the rise of AI.
On this episode, Ryan chats with Vish Abrams, chief architect at Heroku, about all the work that needs to be done after you’ve vibe coded your dream app.
Ryan and Ben welcome Alex Malcoci, CEO and founder of MiniProto, to talk innovations in hardware prototyping, the evolving complexities of the global supply chain, the impact of the US-China trade war on manufacturing, and how automation in production could lead to new training programs for future engineers.
In this special episode, Ryan is joined by our Senior VP of Communities, Philippe Beaudette, and the Trust and Safety team at Stack Overflow to discuss maintaining platform integrity and managing user safety, handling complex issues like harassment, and how their team balances transparency and privacy online.
As a generation characterized as "digital natives," the way Gen Z interacts with and consumes knowledge is rooted in their desire for instant gratification and personalization. How will this affect the future of knowledge management and the technologies of tomorrow?
It’s Java’s 30th anniversary! Ryan welcomes back Georges Saab, Senior VP of Development for the Java Platform Group and Chair of the OpenJDK Governing Board, to reflect on Java’s changes over the last five years.
Ryan Donovan and Ben Popper sit down with Jamie de Guerre, SVP of Product at Together AI, to discuss the evolving landscape of AI and open-source models. They explore the significance of infrastructure in AI, the differences between open-source and closed-source models, and the ethical considerations surrounding AI technology. Jamie emphasized the importance of leveraging internal data for model training and the need for transparency in AI practices.
Ryan and Ben welcome Tulsee Doshi and Logan Kilpatrick from Google's DeepMind to discuss the advanced capabilities of the new Gemini 2.5.
Kathleen Vignos, VP of Software Engineering at Capital One, sits down with Ryan to explore shifting to 100% serverless architecture in enterprise, deploying talent for better customer experience, and fostering AI innovation and tech advancements in a regulated banking environment.
Ryan is joined by Jan Seredynski, Mobile Security Researcher and Pentester at Guardsquare, to talk about how you protect your app when the attackers control the code and the device it runs on.
Snowflake customers can now easily enrich their AI applications and agentic systems with some of the most trusted, highest-quality data available while respecting our community members who provide this content with proper attribution.
Will Wilson, CEO and co-founder of Antithesis, joins Ryan and Stack Overflow senior director of engineering Ben Matthews on the podcast to discuss deterministic simulation testing, the pitfalls of chaos testing in an AI-driven world, and how testing can help developers deal with technical debt.
This year, we're not just collecting data; we're reflecting on the last year of questions, answers, hallucinations, job changes, tech stacks, memory allocations, models, systems and agents—together.
We’re always trying to make it easy for users to pick out the information they need and gain insights into their processes, so a natural language interface seemed like a dream.
Douwe Kiela, CEO and cofounder of Contextual AI, joins Ryan and Ben to explore the intricacies of retrieval-augmented generation (RAG). They discuss the early research Douwe did at Meta that jump started the whole thing, the challenges of hallucinations, and the significance of context windows in AI applications.
Kyle is joined by his former colleague Tyler McEntee, now a senior software engineer at Jona, to talk about doing everything all at once at a startup.
Matthew McCullough, VP of Product for Android Developer Experience, sits down with Ryan to talk advancements in Android development, enhancing developer efficiency and reducing routine toil, and the application of Gemini AI models to improve software toolchains.
As we envision what the ideal future version of Stack Overflow looks like, we’re committed to engaging with our community.
Ryan is joined by Jeremy Edberg, CEO of DBOS, and Qian Li, co-founder of DBOS, to discuss durable execution and its use cases, its implementation using technologies like PostgreSQL, and its applications in machine learning pipelines and AI systems for reliability, debugging, and observability.
An update to the research that the User Experience team is running over the next quarter.
Christophe Coenraets, SVP of Developer Relations at Salesforce, tells Eira and Ben about building the new Salesforce Developer Edition, which includes access to the company’s agentic AI platform, Agentforce. Christophe explains how they solicited and incorporated feedback from the developer community in building the developer edition, what types of AI agents people are building, and the critical importance of guardrails and prompt engineering.
Money is pouring into the AI industry. Will software survive the disruption it causes?
Maryam Ashoori, Head of Product for watsonx.ai at IBM, joins Ryan and Eira to talk about the complexity of enterprise AI, the role of governance, the AI skill gap among developers, how AI coding tools impact developer productivity, what chain-of-thought reasoning entails, and what observability and monitoring look like for AI.