Why intent prediction needs more than an LLM

Why intent prediction needs more than an LLM

Ryan sits down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, though great for language, isn’t the right inductive bias for forecasting human behavior. They discuss how Yobi builds a “foundation model of behavior” using transformers and graph neural networks instead of chat-style LLMs, and what it takes to run millions of personalization decisions per second while keeping consumer data private. Episode notes: Yobi [https://www.yobi.ai/] is a behavioral AI company building foundation models that predict future behavior for ad tech, marketing, and more. Connect with Frank via fportman.com [http://fportman.com] or at yobi.ai [http://yobi.ai]. Congrats to Hooked [https://stackoverflow.com/users/249341/hooked] on winning a Populist badge for their answer to Removing whitespace around a saved image [https://stackoverflow.com/questions/11837979/removing-white-space-around-a-saved-image]. 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].

Code isn’t the only thing causing your production failures

Ryan sits down with Anish Agarwal, CEO and co-founder of Traversal, to chat about why AI coding agents have made writing code easier but running it safely in production harder, why production failures are really caused by interactions between systems and not just the code itself, and how teams can troubleshoot more effectively when traditional observability tools are not enough for agentic AI workflows. Episode notes:  Traversal [https://www.traversal.com/] is an AI-powered autonomous SRE for complex software systems with automatic triage alerts, root cause investigation, and incident prevention at petabyte scale.  Connect with Anish on LinkedIn [https://www.linkedin.com/in/anish-agarwal-io/] or reach out to him at  anish@traversal.com [anish@traversal.com].  Our sixteenth Annual Developer Survey is now open and we want to hear your thoughts on all things software. Take the survey now [https://take.survey.stackoverflow.co/jfe/form/SV_4GHunpL3IfJ3rRc?utm_medium=podcast&utm_source=outreach&utm_campaign=dev-survey-2026&utm_content=launch-survey]! Congrats to user aioobe [https://stackoverflow.com/users/276052/aioobe] on winning a Populist badge for their answer to Javascript a=b=c statements [https://stackoverflow.com/questions/7511279/javascript-a-b-c-statements]. 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].

Oh the places you’ll go with spatial data

Ryan is joined by  Jeffrey Hightower, VP of Places Data at Microsoft, and Amy Rose, CTO of the Overture Maps Foundation, to chat about their partnership in bringing spatial data to the next generation of Microsoft tools; how Overture’s 50 organization members are creating open, standardized, and interoperable  global spatial data sets; and their solutions to the innate challenges of trying to digitally map the world.  Episode notes:  The Overture Maps Foundation [https://overturemaps.org/] is a free, open, and collaborative spatial data platform creating reliable and interoperable map data infrastructure. Microsoft [https://overturemaps.org/about/members/] is a founding member and part of Overture’s Steering committee.  Connect with Amy on LinkedIn [https://www.linkedin.com/in/amynrose/]. Connect with Jeffrey on LinkedIn [https://www.linkedin.com/in/jeffreyhightower/].  Congrats to user Cesar Canassa [https://stackoverflow.com/users/360829/cesar-canassa] for winning a Populist badge for their answer to Slicing a dictionary [https://stackoverflow.com/questions/29216889/slicing-a-dictionary]. 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].

You don’t understand DNS like you think you do

Ryan welcomes Cricket Liu, DNS expert and Chief Evangelist at Infoblox, to the show to talk all things DNS. They cover the evolution of one of the oldest DNS server implementations, BIND, and what the future holds for protected DNS configurations; the realities of security threats like DDoS and DNS spoofing; and why outages often trace back to a lack of understanding of DNS’s fundamental role.  Episode notes: Infoblox [https://www.infoblox.com/] is a cloud-managed network services platform for core networking, combining automated infrastructure management and real-time threat intelligence. You think this is a lot about DNS? Cricket wrote several books [https://www.oreilly.com/pub/au/284] about it.  Connect with Cricket on LinkedIn [https://www.linkedin.com/in/cricketliu/] or email him at  cricket@infoblox.com [cricket@infoblox.com].  Congrats to user Johannes Schaub - litb [https://stackoverflow.com/users/34509/johannes-schaub-litb] for winning a Populist badge for their answer to How do i check if a file is a regular file? [https://stackoverflow.com/questions/328944/how-do-i-check-if-a-file-is-a-regular-file]. 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].

If context is king, architecture is the castle

Recorded live at the AI Agent Conference, Ryan sits down with Apollo GraphQL CEO Matt DeBerglis to discuss how enterprises can leverage GraphQL and MCP as a structured semantic architecture to feed clean data to autonomous agents, safeguard internal microservices against unprecedented "east-west" data exfiltration risks, and rein in skyrocketing token spend by explicitly querying only the exact context required. Episode notes:  Apollo GraphQL [https://www.apollographql.com/] lets you orchestrate APIs with a composable, declarative, self-service model. Apollo's MCP Server is now available. Connect with Matt on LinkedIn [https://www.linkedin.com/in/debergalis/]. 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].