How to know what you don't know?
Who knows!
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing stackoverflow.blog — The Stack Overflow Blog - Stack Overflow From the Network academia.stackexchange.com How to know what you don't know?Who knows! gardening.stackexchange.com Just starting out. Can I plant with winter coming up soon?If only there existed an almanac just for farmers we could check. cooking.stackexchange.com When should I take shrimp off the heat in scampi so it doesn't overcook in the sauce?Long before vibes-based coding, we had vibes-based cooking. stackoverflow.com How can I check whether a lazy import has executed in Python 3.15 without triggering it?They call it Schrödinger’s import. Customer support is the gnarliest AI problemRyan chats with Ahmad Al-Dahle, CTO at Airbnb, about deploying multi-party AI agents to tackle the uniquely gnarly problem of customer support, how a moving target of rigorous evaluations helps engineers balance latency against accuracy, and the ways in which AI coding tools demand an even higher level of judgment from software engineering teams. Releases Delivering controlled and concentrated contextCheck out the new features and capabilities now available in Stack Internal and Stack Internal Community. Try Stack Internal for free by visiting stackinternal.com. Anyone can start building verified knowledge with Stack InternalStack Internal transforms your daily work into a living memory that’s shared with the rest of your team. Now anyone can create and share their knowledge in a Stack Internal workspace for free by visiting stackinternal.com. Elevating security, control, and accessibility: Stack Internal 2026.6In our 2026.6 release, we are shipping updates across administrative security, programmatic API control, developer portal integrations, and platform-wide accessibility—ensuring both your engineers and your AI agents act on verified, decision-grade knowledge. Your trusted knowledge layer: Introducing Stack Internal's new platform experienceIntroducing new Stack Internal capabilities as part of our upcoming platform experience. Our latest release turns your existing foundation of knowledge into enterprise memory that your people, teams, and AI agents can act on. Learn how we’re building the trust layer for enterprise AI. Latest articles The reports of Stack Overflow's death are greatly exaggeratedI’ve seen the recent predictions about Stack Overflow’s demise. They make for compelling headlines, but they confuse a change in how people access knowledge with the disappearance of the knowledge—and the company—behind it. ![]() A JSON schema Is not an AI governance layerThe AI governance argument is happening one layer above the code that actually stops your agent. ![]() Survey Says: You'll swap the model, but everything you build around it is staying putEarlier this month, my team at Stacklok surveyed 520 technical leaders to understand whether they were concerned about being locked into frontier labs. The data says they’re already swapping models in and out, but the trap they’re concerned about is the layer on top of the model. ![]() Production-grade LLMs and agents: a field guideA maturity model for taking agents from an impressive demo to a system people can depend on — with a self-assessment and the map to a deep-dive on each layer. ![]() Why your platform team shouldn't build an AI context layer (even though they probably could)Most engineering teams capable of building an internal AI knowledge system think they should. But six months later, it's a platform team's full-time job. Building an in-house AI context layer costs more money and energy than you think. ![]() Your next job doesn’t have a title yet: Emerging role skills Q&A with Cory Hymel of AndelaWhile the whispers say that everyone is becoming a generalist, that's not where headcount is going. ![]() Beyond the AI noise: How Stack Overflow is rethinking tech hiringIt’s gotten exponentially harder to identify talent that we feel is a good fit for our teams at the top of the application funnel. ![]() A green exit code is not evidence that the work happenedAgents don't build trust for another reason, structurally worse than the first. It isn't only that the tool keeps changing shape. It's that the feedback loop you would need in order to learn the tool is broken at the point of measurement. ![]() A look back before we look forward: A Developer Survey retrospectiveThis analysis compares the 2024 and 2025 Developer Survey data across three connected stories: the evolution of AI, humans at work, and demographics and community. ![]() Organizations need decision-grade knowledge. AI makes it urgent.AI can make the first part remarkably fast. It can find the page, the discussion and the person who might know. The harder work begins when those sources disagree, or when they become stale. ![]() From better privacy to our new ChatGPT plugin, here's what's new on Stack Overflow for AgentsWe've learned a lot in the last three months since launching Stack Overflow for Agents, our API-first knowledge exchange for agents. Here's a few of our findings, what's new on the platform (including our new ChatGPT plugin), and how we're continuing to build Stack Overflow. ![]() (Re)introducing Developer StoryFor the past few years, we’ve been looking at ways to bring a little more of the individual developer back to Stack. ![]() Responsible AI adoption needs developer workflow designOrganizations cannot solve shadow AI with a document employees read once. They need to make responsible use easier than improvised use. ![]() Dispatches from O'Reilly: The right amount of spec for agentic developmentWhen code gets cheap, the hard part is deciding what “correct” means and building a reliable way to check it. ![]() More Podcast Around the web carlhandellen.substack.com An AI rantThe rumors of humanity’s death at the hands of AI have been greatly exaggerated. nullpt.rs Why is this fingerprinting script creating bioweapons?Well that’s one way to stop bots from scraping. worksinprogress.co The forgotten formula for lovable citiesWe must stop the ensh*ttification of our cities. nbcnews.com Tesla to wind down Cybertruck productionIt appears the low-poly rendering experiment has finally failed its real-world rendering test. newsletter.signoz.io AI isn't replacing SREs, it's deskilling themOr the more terrifying option: never-skilling. github.com Astroterm: A planetarium for your terminalFinally, a way to look at the stars without the terrifying requirement of having to go outside. techpolicy.press Breaking the open web won't stop the bad botsIt’s kind of like throwing the baby out with the bathwater. labs.ycombinator.com We ran AI agent swarms in Minecraft and MindustryIt’s not procrastinating if you’re playing Minecraft for research purposes. pepsipu.com Jailbreaking the Switch2It's a-me, agentic Mario! modelcompare.ai Every AI model has the same “controversial” take on humansHow ironic that the sycophantic AI models think we're too sycophantic. henrikkarlsson.xyz How is music possibleMusic can literally alter our realities. edjefferson.com Local Wikipedia is Wikipedia, but only for things a half hour walk from youFinally, a Wikipedia to settle arguments about what that weird building down the street used to be. Want updates to your inbox? Every week we’ll share a collection of great questions from our community, news and articles from our blog, and awesome links from around the web. |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |