Stack Overflow

🎙️ We welcome Saahil Jain @saahil9jain, CTO of @youdotcom, to the show to discuss why building agents with a 2024 mindset is a mistake, why heavy orchestration layers can hurt model performance more than help it, and why the 2026 competitive edge actually comes from information retrieval. stackoverflow.blog/2026/07/07/age…

For 15 years, the Stack Overflow Developer Survey has tracked how the tech world actually works 🌐 This year, we want your honest take on everything from your favorite programming languages to whether autonomous agents are actually helping you code—or just making a mess. Have your voice heard in this year's #DeveloperSurvey results: take.survey.stackoverflow.co/jfe/form/SV_4G…

Signature-based detection works exactly as designed, but attackers don't. Machine learning and autonomous agents are changing detection entirely, shifting from "does this match a known pattern?" to "does this actually make sense in context?" From The Heap, Samaresh Kumar Singh breaks down how SnortML and agentic AI work together to catch novel attacks in context. stackoverflow.blog/2026/07/06/whe…

🎙️ We welcome Benny Chen @the_bunny_chen, co-founder of @FireworksAI_HQ, to the show to explore what actually makes an AI application good or not, how to balance qualitative signals with quantitative metrics when evaluating AI, and how open-source eval protocols and community efforts are setting the standard for AI evaluation. stackoverflow.blog/2026/07/03/the…

🎙️ We sit down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, is great for language but isn’t right for forecasting human behavior, how Yobi builds a “foundation model of behavior” using transformers, and what it takes to run millions of personalization decisions per second while keeping consumer data private. stackoverflow.blog/2026/06/30/why…

🎙️ In this episode of Leaders of Code recorded at Snowflake Summit, we're joined by Vivek Raghunathan, SVP of engineering at Snowflake, to chat about the five-stage framework his org used to go from "let chaos reign" to a repeatable, org-wide system for AI-assisted engineering; how Snowflake used "focus weeks" to push the frontier further; and how Snowflake cut release validation time from 15 days to a single day. stackoverflow.blog/2026/07/02/ai-…

While agentic AI use is becoming more and more common in our modern software development lifecycle, developers in senior executive (50%) and software architect (52%) roles are by far the most likely to use AI agents on a daily basis. Academic researchers seem the most hesitant to adopt agents, with 22% not using AI-assisted tech at all. Explore more results from our latest #StackOverflowKnows survey: stackoverflow.blog/2026/05/27/age…

🎙️ We sit down with Anish Agarwal @_anish_agarwal, CEO of @traversal_ai, to chat about why AI coding agents have made writing code easier but running it safely in production harder, what's really causing production failures (spoiler: it's not just code), and how teams can troubleshoot more effectively when traditional observability tools fall short with AI workflows. stackoverflow.blog/2026/06/25/cod…

For the last decade and a half, the Stack Overflow Developer Survey has been a pulse check on the developer community 💻 This year, we want to know your thoughts on everything software, from your favorite programming languages to what it's really like to use autonomous agents. Learn more about our Annual #DeveloperSurvey and add your voice to this year results: stackoverflow.blog/2026/06/23/the…

When high-stakes agents—ones that can move around money or edit critical records—are built with human-in-the-loop review processes, human error caused failures are inevitable. But what if we built these agents around responsibilities, not capabilities? In this Dispatch from @OReillyMedia, Artur Huk explores the Responsibility-Oriented Agent framework and how it could be the solution to our alert fatigue. stackoverflow.blog/2026/06/19/dis…

It's probably no surprise that daily AI agent use has skyrocketed since our 2025 #DeveloperSurvey. According to our May survey on agentic AI in the workplace, more than a third of developers are using autonomous AI tools everyday in their work. But the number of respondents who don't use or plan to use AI has also increased, now accounting for 21% of developers. Explore more results from our latest #StackOverflowKnows survey: stackoverflow.blog/2026/05/27/age…

Your agent is spending compute time and precious tokens to brute-force a solution that another agent already figured out. That's why we built Stack Overflow for Agents, an API-first exchange that lets your AI agents ask questions, share their learnings, and validate their blueprints, so you can close the gap between static training data and the realities of production software. Learn more about Stack Overflow for Agents and join the beta: stackoverflow.blog/2026/06/10/ann…

It’s finally here—our sixteenth Annual Developer Survey is now open! 🚀 From your favorite programming languages and tools, to the AI coding assistants you rely on, to the ways you’re building community and learning about new tech, we want to hear your thoughts on all things software. Take the 2026 #DeveloperSurvey here: take.survey.stackoverflow.co/jfe/form/SV_4G…

🎙️ We welcome Cricket Liu @cricketondns, DNS expert and Chief Evangelist at @Infoblox, to the show to talk the evolution of one of the oldest DNS server implementations BIND, 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. stackoverflow.blog/2026/06/19/you…

We're doing a happy dance because it's nearly here—the 2026 #DeveloperSurvey is dropping this week! 👾 Here's a pre-survey question for devs: what are you most excited to learn from the survey this year? Explore the results of last year's Developer Survey: survey.stackoverflow.co/2025?utm_mediu…

Dear @mipsytipsy...how do I get my leaders to stop running teams into the ground? In this first issue of Charity Majors' advice column, Charity helps a senior staff engineer navigate one of the hardest problems in software engineering: right-sizing work when leadership is asking you to push past your capacity. stackoverflow.blog/2026/06/12/wha…

🎙️ From the floor of the AI Agent Conference, we're joined by @apollographql CEO Matt DeBergalis to chat about clean data for your AI agents, how to safeguard your internal microservices from "east-west" data exfiltration, and why explicit querying with exact context can reign in your skyrocketing token spend. stackoverflow.blog/2026/06/16/if-…

Engineering teams are upgrading their tools with faster and smarter AI. But have they upgraded how they work? Eira May explores how old processes are the new bottleneck for AI-assisted workflows and the actionable steps engineering leaders can take to transform and evolve those tired processes. stackoverflow.blog/2026/06/18/the…

Documentation remains an important part of development, even as AI changes how devs interact with code. Last year, GitHub was the most desired collaboration tool, with 59.3% of developers wanting to use it for documentation. Meanwhile, Markdown (75.8%) remained the most admired documentation tool for the third year in a row. How do you think agentic workflows will change these numbers in 2026? Explore more findings from our 2025 #DeveloperSurvey: survey.stackoverflow.co/2025/?utm_medi…

AI agents are confused deputies, and they pose a real security threat when we give them the keys to our kingdoms. That's what happened with the recent Instagram breach, when hackers got control of more than 20,000 accounts using the Meta AI support agent. In this piece from The Heap, Fabio Salvadori explores what happened during that breach and why human judgement in our code is more important than ever. stackoverflow.blog/2026/06/17/ai-…