What the Dev? is a podcast by the SD Times editorial team. We cover the biggest and newest topics in software and technology.
Similar Podcasts
Thinking Elixir Podcast
The Thinking Elixir podcast is a weekly show where we talk about the Elixir programming language and the community around it. We cover news and interview guests to learn more about projects and developments in the community.
Rocket
Countdown to excitement! Every week Christina Warren, Brianna Wu and Simone de Rochefort have accelerated geek conversation. Tech, comics, movies, games and books, no galaxy is off limits! Hosted by Christina Warren, Brianna Wu, and Simone De Rochefort.
Rustacean Station
Come journey with us into the weird, wonderful, and wily world of Rust.
358: The limitations of AI models in understanding context (With Jonathan Macoskey)
Dave Rubinstein and Jonathan Macoskey discuss the limitations of current AI models in understanding context, particularly in enterprise settings. Macoskey explains that while language models have improved with internet connectivity, they still struggle with outdated information and proprietary data. He highlights Lovelace's context engine, which integrates data from various sources into a knowledge graph, addressing issues like entity resolution and recall. This system ensures AI agents can provide accurate, cited information, enhancing trust and decision-making. The conversation also touches on the challenges of scaling large language models and the importance of grounding AI responses in reliable data.
357: Why is REST connectivity still hard? (With Kumar Vikesh)
Dave Rubinstein, Editor in Chief of SD Times, discusses with Kumar Vikesh, Senior Product Owner at Progress Data Direct, the challenges of REST connectivity and the introduction of an AI-driven solution to automate the creation of model files for the Autonomous REST Connector. Progress Data Direct offers a standard connectivity platform with over 60 connectors and 100 data sources. The new AI-driven approach uses three agents: a generator, validator, and launcher, to create, validate, and test REST model files, reducing manual effort from days to hours. The solution is currently in an early access program, with plans for future general availability and integration with Visual Studio Code.
356: REPRESENTATIVE!!! The State of Real-Time Voice AI Technology (With Mike Pappas)
Dave discusses real-time voice AI with Mike Pappas, CEO of Modulate. Pappas explains that voice AI involves three key technologies: speech-to-text, language models, and text-to-speech. This technology is valuable in detecting fraud, ensuring policy adherence, and routing calls efficiently.
355: Managing costs and ROl of agentic Al initiatives (With John D'Emic)
In this episode, Dave speaks with John D'Emic, cofounder and CTO at Revenium, about the challenges organizations face in managing costs and ROI of agentic AI initiatives. John explains that the transition from pre-production to production often reveals gaps in economic visibility, leading to "agent debt" due to unanticipated costs from API calls and tool usage.
354: Challenges and Misconceptions around Vibe Coding (With Cameron Etezadi)
In this episode with Dave Rubinstein, Cameron Etezadi, CTO of LaunchDarkly, discussed the challenges and misconceptions around Vibe coding. He highlighted that while code production has sped up, confidence in the quality of the code has decreased, with 91% of customers being less confident. He noted that 94% of customers are shipping more code but struggle with validation and quality.He noted that 94% of customers are shipping more code but struggle with validation and quality.
353: Why Your Zoom Calls Freeze Despite Good Wi-Fi
This week, Dave discusses the issue of Zoom calls freezing despite good Wi-Fi with Shafi Khan, Principal Engineer at Cable Labs. Khan explains that the problem arises from a lack of bi-directional communication between applications and networks. Shafi introduces the Quality by Design framework based on intent-based APIs, which allows for real-time telemetry and end-to-end metrics. He explains the use of the open-source entity Kamara to provide APIs for developers and application builders.
352: Anthropic's Mythos Project and AI Vulnerabilities
In this episode, Dave Rubinstein speaks with Jaya Baloo, founder, COO and CISO at cybersecurity provider AISLE, about the implications of AI models like Anthropic's Mythos, which can discover and exploit vulnerabilities. The conversation touches on the existing challenges defenders face in keeping up with the volume of vulnerabilities, suggesting that AI has not made the situation worse but rather highlighted it.
351: Challenges and Progress of AI in Enterprise Production
In this episode, Dave Rubinstein, editor-in-chief of SD Times, sits down with Karthik Sj, General Manager of AI at LogicMonitor, to discuss the challenges and progress of AI in enterprise production. Among the topics discussed are:* The rapid advancements in AI, particularly in code generation and self-healing* Emphasizing the importance of context engineering and agent execution engines* Recommending that organizations start with an automation readiness report to assess their maturity and tailor their AI adoption roadmap
350: Multi-model AI Orchestration
In this episode, Dave speaks with Mike Sirchuk, president, founder and CEO of Swa Technology, about providing organizations with multiple AI models to choose from, and bringing those tools to where people work today, such as in Slack teams, text messaging and Zoom, to name a few. The Swa platform also enables companies to build the security layer to manage who has access to what model.
349: Addressing AI bottlenecks in Agentic Development (with Kenneth Ziegler)
In this episode, Dave talks with Kenneth Ziegler, CEO of Leapwork, about the findings of a survey on AI in testing, revealing that while 88% of companies are developing agentic software, only 13% are using AI for testing. He highlighted that 59-60% of testing remains manual, presenting an opportunity for AI to streamline processes. Ziegler emphasized the importance of speed, ease, and quality in AI adoption. He introduced Leapwork's new AI Studio, which integrates traditional no-code testing with AI-native continuous validation, aiming to address bottlenecks in agentic development by ensuring deterministic outcomes.
348: MCP and AI Strategy Heartburn
In this episode, SD Times editor-in-chief Dave Rubinstein speaks with Adam Seligman, CTO at Workato, about MCP and what Adam is calling AI strategy heartburn.Seligman compares the current AI adoption to overeating at a buffet, emphasizing the need for a healthy approach to AI. He explains the magic of AI when it works but also its tendency to hallucinate or provide incorrect answers, likening it to the need for secure and trusted human interactions.
347: Application Security in the Age of Agentic AI Development (With Eran Kinsbruner of Checkmarx)
Traditional AppSec tools were created with the assumption that humans wrote code and security reviewed it afterward. But when AI generates code continuously and autonomously, at a speed no traditional security process can keep up with, vulnerabilities spread long before a scanner ever runs. Risk is compounding while security struggles to catch up. In this episode, Dave Rubinstein speaks with Eran Kinsbruner, vice president of marketing at AppSec company Checkmarx. Among the topics discussed are:-- Why traditional AppSec tools can't keep pace with AI-generated code-- The need to ensure security from the beginning of the project-- How the SDLC is morphing into assn ADLC -- Agentic Development Life Cycle
346: Where AI in QA is Actually Working Today (with Digital.ai's Derek Holt)
In this episode, Dave speaks with Derek Holt, CEO at digital.ai, to discuss how AI should be used in testing to give organizations the most value.In this podcast, they talk about:-- How AI pays off when it handles pattern-heavy, low-judgment work-- How fully autonomous, “one-click” QA has issues-- What organizations can do to get started using AI in software testing
345: What hiring managers are looking for in developers in 2026 (with Cribl's Sydnee Mayers)
In this episode, Dave interviews Sydnee Mayers, product lead at Cribl, about the skills developers need to thrive in 2026.They discuss:How the development role is changingThe specific skills developers need going forwardHow organizations should handle the speed at which things are changing
344: Why developers should adopt a head chef mentality to work with agents (with Confluent's Adi Polak)
In this episode, Jenna interviews Adi Polak, director of advocacy and developer experience engineering at Confluent, about why developers need to embrace a head chef mindset when working with AI agents.They discuss:What it means to adopt a "head chef" mindsetThe mental shifts needed to work this wayWhat role data streaming plays in enabling this