RSS Reader

Alex Martsinovich argues that agentic coding causes four unavoidable harms - slop, alienation, deskilling, and team breakdown — but these aren't technological inevitabilities, they're the results of specific choices about how to use AI coding tools.

Nolan Lawson explores why developers often build custom solutions instead of using native APIs, largely looking at JavaScript, but it's something that shows up in most languages and environments, for good reason.

Starting with IntelliJ IDEA 2026.3 and Android Studio Rabbit 2 | 2026.2.2, we’re discontinuing Swift language IDE features in the Kotlin Multiplatform (KMP) plugin. This includes editing, syntax highlighting, and navigation within Swift files and between Swift and Kotlin. Running iOS applications and debugging Kotlin code on iOS will remain fully supported. Kotlin/Native functionality, such […]

Configuration drift refers to the disparity between configurations as coded in repositories like Git and what’s actively deployed. Despite embracing continuous integration and continuous deployment (CI/CD) methodologies, modern software organizations still grapple with this disparity, which not only complicates deployments but can also jeopardize the stability of production environments. For example, imagine a scenario where a Continuous Deployment (CD) pipeline deploys an application to a...

Here's a product feature which the world is going to need a whole lot more of over the coming months and years: default hard budget caps. I'm talking about the feature of pay-by-usage services and APIs that lets you say "after $X/month, cut this thing off and return errors". These need to be hard limits. Soft caps, "after $X/month, send me a warning email", will not cut it. Coding agents, and personal agents (coding agents wrapped in a less threatening UI), greatly reduce the friction of...

I just sent the September edition of my sponsors-only monthly newsletter. If you are a sponsor (or start a sponsorship now) you can access it here. This month: More Fable class models A pricing war 3D graphics, Blender, and pixel art LLMs come for mathematics So many more accidental cyberattacks The vulnapocalypse comes for Datasette What I'm using right now My software releases this month 2026 in LLMs (so far) Here's a copy of the August newsletter as a preview of what you'll get. Pay...

Prefer pure functions for rules and closures for construction. Classes should solve a concrete problem, not become the default shape of application code.

Museum: Rex's Dino Store Located just before the turnstiles in the Grand Army Plaza subway station at the north end of Brooklyn's Prospect Park is this former newsstand which is now operated by a dinosaur. The density of dinosaur puns is exceptional. Tags: art, new-york

It's simply impossible to not hear about Jev. Seemingly everyone is tinkering with it in some way, from using it to make trading decisions (what could possibly go wrong?) to generating UIs with it (maybe we're onto something here!). Jev is a new kind of AI model. You feed it data and ask it a set of multiple-choice questions, and it responds with its answers and how confident it is in each. Just like with any other model, Jev can and will make mistakes, but it will make them fast. The bottom...

Speed Insights is deprecating First Input Delay (FID) and will stop recording new measurements on November 1st. Speed Insights already uses Interaction to Next Paint (INP), the Core Web Vital that replaced FID, as the responsiveness metric in your Real Experience Score. The deprecation won’t require changes on your side, affect your score, or prevent you from viewing existing FID data. Learn more in the Speed Insights metrics documentation. Read more

Rogo on Vercel 73,000+ deployments in a single month Agent-written code shipped to production in 5 minutes 6 production AI agents automating work from churn analysis to deal desk Zero manual triage during production incidents with agent swarms on AI SDK Rogo builds Felix, an AI agent that generates decks, financial models, and reports for a majority of the world's largest financial institutions. The Rogo team is rearchitecting its internal applications on Vercel, where agent-written code...

W3C President and Interim CEO Dominique Hazaël-Massieux shares timely and notable highlights and information selected from the busy and prolific work last month at W3C.

With Rust 1.100.0, the following changes to 32-bit Windows targets will happen: i686-pc-windows-msvc Tier 1 with host tools target will be demoted to Tier 1 without host tools. i686-pc-windows-gnu Tier 2 with host tools target will be demoted to Tier 2 without host tools. Builds of the standard library will continue to be distributed, but host tools such as the compiler will be no longer available. i686-pc-windows-msvc as a Tier 1 target still undergoes CI testing. To build 32-bit Windows...

Spring AI: RAG Doc | Jev Doc | Demo In the previous article we introduced Spring AI TypeSafe and its Jev model: typed questions in, calibrated numbers out, in a few hundred milliseconds. One row in that article's SPI table deserves its own post. JevDocumentFilter and JevDocumentReranker are DocumentPostProcessors, which means they plug straight into Spring AI's Modular RAG pipeline. This article puts the two together. Two LLM calls clean up and multiply the user's question before retrieval....

Laya from Convai Innovations is free to use on AI Gateway for 1 month through October 31, 2026 via Boundless. Laya is an evaluation/decision model that evaluates shared context against yes/no, choice, or scoring questions and returns structured answers with probabilities. For example, use it to: Triage support requests: Detect a refund request and route it to the billing team. Route agent work: Choose which tool or workflow should handle a request. Check guardrails: Flag a request or...

Vercel and Microsoft AI (MAI) have partnered to make MAI models available on AI Gateway. AI Gateway is one of a limited number of platforms offering access to MAI models. MAI's focus on security and zero data retention (ZDR) align with Vercel's goal of giving AI Gateway users control over their data and transparency in how it is used for training. MAI models on AI Gateway MAI's latest audio models are now supported on AI Gateway. MAI-Voice-2.1 and MAI-Voice-2.1-Flash generate speech, while...