The Stack Overflow Podcast

The fastest agent in the race has the best evals

Ryan welcomes Benjamin Klieger, lead engineer at Groq, to explore the infrastructure behind AI agents, how you can turn a one-minute agent into a ten-second agent, and how they used fast inference and effective evals to build their efficient and reliable Compound agent.  Episode notes:  Groq [https://groq.com/] delivers fast, low-cost inference using their custom-designed LPU, the first chip built for inference. Check out their agent, Compound [https://console.groq.com/docs/compound/systems/compound], which can search the web and run code. Connect with Benjamin on LinkedIn [https://www.linkedin.com/in/benjamin-klieger/] and X [https://x.com/benklieger].  Congrats to user Bart Kiers [https://stackoverflow.com/users/50476] for winning a Stellar Answer badge on their response to Regular expression to match a line that doesn't contain a word [https://stackoverflow.com/questions/406230/regular-expression-to-match-a-line-that-doesnt-contain-a-word].  See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

One thing enterprise AI projects need to succeed? Community.

In this episode of Leaders of Code, Stack Overflow CEO Prashanth Chandrasekar chats with Ramprasad Rai, VP of Platform Engineering at JPMorgan Chase & Co., about the unique challenges of implementing AI in an enterprise environment. They discuss how organizations can balance AI-driven productivity with strict compliance and security requirements by leveraging a community-driven knowledge system that grounds probabilistic AI tools in internal, trusted expertise. The discussion also: * Explores why AI models often hallucinate in enterprise environments due to a lack of internal context.  * Highlights how Stack Overflow’s structured Q&A data provides ideal fine-tuning material for the next generation of AI models. Notes * Connect with Ramprasad Rai [https://www.linkedin.com/in/irnlogic/] on LinkedIn. See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

AI code means more critical thinking, not less

Ryan is joined by Secure Code Warrior’s co-founder and CTO Matias Madou to discuss the implications of LLMs’ variability on code security, the future of developer training as AI coding assistants become more popular, and the importance of critical thinking—especially for junior developers—in the age of AI. Episode notes:  Secure Code Warrior [https://www.securecodewarrior.com/] upskills development teams to help companies stay protected against potential cybersecurity threats. Connect with Matias on Linkedin [https://www.linkedin.com/in/matiasmadou/].  Shoutout to Lifejacket badge winner Sergey Kalinichenko [https://stackoverflow.com/users/335858/sergey-kalinichenko], who won the badge for their answer to K&R Code for getting an int [https://stackoverflow.com/questions/37553055/kr-code-for-getting-an-int]. TRANSCRIPT [https://stackoverflow.blog/2025/11/11/ai-code-means-more-critical-thinking-not-less/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

Revealing the unknown unknowns in your software

Ryan welcomes Nic Benders to discuss the complexity and abstraction crisis in software development, the importance of going beyond observability into understandability, and demystifying AI's opacity for understanding and control. Episode notes: New Relic [https://newrelic.com/] is a full-stack observability platform that helps engineers plan, build, deploy, and run software. Read their 2025 observability forecast. [https://newrelic.com/resources/report/observability-forecast/2025]  Connect with Nic on Linkedin [https://www.linkedin.com/in/benders/] or email him at nic@newrelic.com. Congratulations to user Yochai Timmer [https://stackoverflow.com/users/536086/yochai-timmer] for winning a Populist badge on their answer to Reader/Writer Locks in C++ [https://stackoverflow.com/questions/244316/reader-writer-locks-in-c].  See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

To write secure code, be less gullible than your AI

Ryan is joined by Greg Foster, CTO of Graphite, to explore how much we should trust AI-generated code to be secure, the importance of tooling in ensuring code security whether it’s AI-assisted or not, and the need for context and readability for humans in AI code. Episode notes: Graphite [https://www.graphite.dev/] is an AI code review platform that helps you get context on code changes, fix CI failures, and improve your PRs right from your PR page.  Connect with Greg on LinkedIn [https://www.linkedin.com/in/gregmfoster/] and keep up with Graphite on their Twitter [https://x.com/graphite/].   This week’s shoutout goes to user xerad [https://stackoverflow.com/users/22756042/xerad], who won an Investor badge by dropping a bounty on the question How to specify x64 emulation flag (EC_CODE) for shared memory sections for ARM64 Windows? [https://stackoverflow.com/questions/79760904/how-to-specify-x64-emulation-flag-ec-code-for-shared-memory-sections-for-arm64]. TRANSCRIPT [https://stackoverflow.blog/2025/11/04/to-write-secure-code-be-less-gullible-than-your-ai/] See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].