InfoWorld AI·
For nearly as long as the web has existed, web development has wrestled mightily with the right way to connect components over the network. This is the question of the remote API. It influences every aspect of the software we build. We sort of arrived at a tolerable compromise with JSON APIs. While these have their limitations, you have to appreciate their underlying simplicity. But the advent of AI-enabled endpoints that can mediate intent is changing the basic workings of the internet. This change is gradually reawakening an old dream, the service-oriented architecture (SOA). This time around, with luck, we’ll finally gain the flexible, discoverable, and maintainable automated service discovery we’ve longed for. Fingers crossed. Why old-school SOA failed Let’s call this burgeoning influence of AI on web architecture SOA 2.0. To understand why SOA 2.0 is different from SOA 1.0, we have to remember the trauma of the 2000s. (This may be painful but also cathartic.) The original dream o
Read full articleAI is booming. New use cases are emerging each day. To capitalize on the technology’s potential, enterprises require data at scale. In many cases, though, the relevant information is blocked or unstructured, which limits its use by AI models. To understand this challenge, consider the foundation of the web itself. The web was not designed…
Most people used ChatGPT like a smarter search engine. Ask a question, get an answer, and move on. It works but it leaves a surprising amount of value on the table. Over the past few years, ChatGPT has evolved far beyond a simple chatbot. It can browse the web, analyze files, generate images, maintain memory, […] The post Most People Use ChatGPT Wrong: 10 Features and Tips That Changed How I Work appeared first on Analytics Vidhya.
How Notion uses Codex to one-shot specs, build AI Voice Input for the web, and multiply engineering power across small teams.
Where are we in the historical cycle? And what’s next?
The first mobile application user interfaces were often scaled-down versions of what was already available on the web. Then, user experience (UX) designers recognized that the different smartphone form factor created new business opportunities and greater utility compared to what people were doing on their desktops. UX designers created mobile-first experiences tailored to the job to be done and other design thinking principles. The underlying agile development practices, along with the emergence of app stores, paved the way for explosive growth in smartphones and mobile applications. Today’s AI experiences seem to be following a similar path, with basic, sometimes bolted-on user experiences. First-gen chatbots appeared as pop-ups with text entry-and-response user interfaces (UIs) overlaid on the application’s screens. The primary UI for large language models (LLMs) is often a text box that accepts a prompt followed by a response that includes text and other media. Early AI agents were
An image generated by ChatGPT Images 2.0. | Image: OpenAI OpenAI is rolling out the latest version of its AI-powered image generator with new "thinking capabilities," allowing it to search the web to help it create multiple images from a single prompt. In a blog post, OpenAI says ChatGPT Images 2.0 can now create more "sophisticated" images, with improvements to its ability to follow instructions, preserve details of your choosing, and generate text. It's powered by OpenAI's new GPT Image 2 model, with new thinking capabilities available to ChatGPT Plus, Pro, Business, and Enterprise subscribers. When a thinking model is selected, the chatbot's image generator can pull information from the web, cr … Read the full story at The Verge.
As companies move from experimenting with AI agents to deploying them in production, one pattern becomes clear: capability without control is a liability. Agents operate in long-running, stateful environments. They browse the web, read repositories, execute shell commands, call APIs and interact with internal systems. That power is transformative — and it meaningfully expands the attack surface. In a recent interview, Jonathan Wall, CEO of Runloop, summarized the shift: “By default, agents should have access to very little. They need to do real work, but capabilities have to be layered on in a controlled way.” That framing reflects a broader industry reality: agent infrastructure must be designed around least privilege, explicit isolation and observable execution. What follows is a practical control architecture for production agents. The layered control model A resilient agent deployment combines six explicit layers: Strong runtime isolation with a microVM Restrictive network policy w
Today’s upgrades for AI Mode in Chrome transform how you interact with the web
