The Stack Overflow Podcast

Your tokenmaxxing is not valuemaxxing

29 min · 11 aug 2026
aflevering Your tokenmaxxing is not valuemaxxing artwork

Beschrijving

Ryan is joined by Coder’s Rob Whiteley to chat about why tokenmaxxing isn’t proving real value and just triggering Goodhart’s Law, how release speed and PR merges can help you measure agentic outcomes with or without a human-in-the-loop, and what the democratization of skills means for junior developers and the talent pipeline.  Episode notes: Coder [https://github.com/coder] is a self-hosted platform that lets you securely run cloud development environments and AI coding agents on your own internal infrastructure.  Connect with Rob on LinkedIn [https://www.linkedin.com/in/rwhiteley/]. Today’s shoutout goes to an Unsung Hero badge winner, user Red.Wave [https://stackoverflow.com/users/6385640/red-wave]! 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].

Reacties

0

Wees de eerste die een reactie plaatst

Meld je nu aan en word lid van de The Stack Overflow Podcast community!

Probeer gratis

Probeer 30 dagen gratis

€ 9,99 / maand na proefperiode. · Elk moment opzegbaar

  • Podcasts die je alleen op Podimo hoort
  • 20 uur luisterboeken / maand
  • Gratis podcasts

Alle afleveringen

973 afleveringen

aflevering Your tokenmaxxing is not valuemaxxing artwork

Your tokenmaxxing is not valuemaxxing

Ryan is joined by Coder’s Rob Whiteley to chat about why tokenmaxxing isn’t proving real value and just triggering Goodhart’s Law, how release speed and PR merges can help you measure agentic outcomes with or without a human-in-the-loop, and what the democratization of skills means for junior developers and the talent pipeline.  Episode notes: Coder [https://github.com/coder] is a self-hosted platform that lets you securely run cloud development environments and AI coding agents on your own internal infrastructure.  Connect with Rob on LinkedIn [https://www.linkedin.com/in/rwhiteley/]. Today’s shoutout goes to an Unsung Hero badge winner, user Red.Wave [https://stackoverflow.com/users/6385640/red-wave]! 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].

11 aug 202629 min
aflevering How to be fearlessly AI native artwork

How to be fearlessly AI native

Ryan welcomes McLaren Stanley, Senior Principal Engineer for Amazon Stores, to discuss what it actually takes to make teams AI native, why agentic engineering is shifting code bottlenecks downstream to testing and deployment, and why robust validation is essential to build trust and enable “fearless commits.” Episode notes: You can learn more about how Amazon’s frontier teams became AI native on the AWS blog [https://aws.amazon.com/blogs/machine-learning/how-frontier-teams-are-reinventing-ai-native-development/].  Connect with McLaren on LinkedIn [https://www.linkedin.com/in/bmclarenstanley/]. Congrats to user o11c [https://stackoverflow.com/users/1405588/o11c] for winning a Populist badge for answering Pythonic way to count the number of trailing zeros in base 2 [https://stackoverflow.com/questions/40608220/pythonic-way-to-count-the-number-of-trailing-zeros-in-base-2].  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].

7 aug 202640 min
aflevering Your MVP doesn’t need a Kubernetes cluster artwork

Your MVP doesn’t need a Kubernetes cluster

Ryan welcomes Anurag Goel, CEO and co-founder of Render, to discuss why most startups shouldn’t start by managing their Kubernetes and cloud infrastructure. They discuss how frustration with spinning up nodes at Stripes led him to build a company, a future where your application itself may allocate its own compute, and why DevOps jobs aren’t going anywhere.  Episode notes Render [https://render.com/] calls itself the cloud for builders, intuitive infrastructure for scale.  Connect with Anurag at anurag@render.com [anurag@render.com].  Congrats to Populist badge winner Hovercraft Full Of Eels [https://stackoverflow.com/users/522444/hovercraft-full-of-eels] for bringing the knowledge to How can I disable System.out for speed in Java [https://stackoverflow.com/questions/9882487/how-can-i-disable-system-out-for-speed-in-java/9882559#9882559]. 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].

4 aug 202631 min
aflevering What happens to the internet when robots act like humans? artwork

What happens to the internet when robots act like humans?

Ryan welcomes WPEngine CTO Ramadass Prabakar to the show to chat about what happens—and what we should do—when agents start acting like humans online, how our internet is evolving to serve both human and agentic experiences from the same interface, and what we can do to differentiate and protect human actions online from malicious bot activity.  Episode notes:  WP Engine [https://wpengine.com/] hosts and manages over 5 million WordPress sites, combining enterprise-grade software, developer tools, and cutting-edge AI to support your website. Connect with Ramadass on LinkedIn [https://www.linkedin.com/in/ramadassprabhakar/] or Twitter [https://x.com/ramadassp]. Congrats to user Nama [https://stackoverflow.com/users/1093221/nama] on winning a Famous Question badge for asking how to store the spinner values into database? [https://stackoverflow.com/questions/8831349/how-to-store-the-spinner-values-into-database] 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].

31 jul 202630 min
aflevering You need reliable AI context for your site reliability artwork

You need reliable AI context for your site reliability

Ryan is joined by Asaf Savich, Komodor’s AI Engineering Group Manager, to discuss why modern reliability work requires navigating massive cross-service context, what good context engineering actually likes when AI is integrated into site reliability, and how the work of human SREs is shifting towards strategy and AI agent management. Episode notes:  Komodor [https://komodor.com/] is an autonomous AI SRE platform designed to troubleshoot, manage, and optimize Kubernetes-based cloud-native infrastructure.  Connect with Asaf on LinkedIn [https://www.linkedin.com/in/asaf-savich/].  Congrats to Populist badge winner joemaller [https://stackoverflow.com/users/503463/joemaller], who won the badge for answering Is there a Python equivalent to the 'which' command [https://stackoverflow.com/questions/9877462/is-there-a-python-equivalent-to-the-which-command]. 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].

28 jul 202626 min