AIQB · RSS Feed

The failure nobody demos The agent demo always works. The customer asks for a refund, the...

Review Pull Requests with Kiro CLI and GitHub Actions Kiro CLI has a headless mode. Give...

GPU memory can be installed yet restricted. Kate's CMP 170HX research separates effective configuration, intact HBM and a scoped arithmetic benchmark.

How to make a quality drop fail your build with agents-cli eval run and one threshold, for anyone who ships an agent from a pipeline.

I build plenty of apps due to the nature of my job. I use coding agents extensively. I decide what...

How did I build and deploy 3 fully functional apps while still in college, before I even landed my...

A few years ago, writing code was one of the hardest parts of being a software developer. Today, AI...

If you’ve been in the software industry for any length of time, you’ve probably heard people talking...

My life used to live in ten different apps. A to-do app. A calendar. A budget spreadsheet. A notes...

Answer: a thirty-second AI video costs between about $0.30 and $6.30 depending on model and...

Memory is what the agent knows: the context the model sees right now, plus anything you carry across...

n8n Labs has introduced Nod, a standalone personal agent that runs on a user's own computer and can...

n8n has released Nod, a standalone personal agent designed to run on a user's computer rather than...

Genkit and ADK save every turn of your agent's conversation, tool responses included, in a store you never designed. What ends up in there, why you can't sanitize your way out, and why fixing it is the framework's job.

Benchmark headlines are easy to share and hard to check. In July, LiteLLM published benchmarks for...

My MacBook Air started restarting by itself. The 512 GB disk was full, and most of what filled it...

No medication app fit how I take my pills, so I built one. Vzato went from an empty folder to App Store review in about 20 hours and was approved two days later, for iPhone, iPad and Mac. What the AI did, what I did, and what went wrong.

TL;DR: Global Hack Map is a free, MIT-licensed live map of publicly reported cyberattacks, data...

Anthropic shipped Claude Fable 5.2 and cut its price by 20%. Meta launched Muse Ember, a tiny-priced...

The 90% AI Code Quota: Why Big Tech Is Manufacturing Fragile Codebases Imagine being a...

Seven months ago Anthropic claimed thousands of high-severity AI-discovered bugs. The independent audit is in: 37,966 findings, 7,349 public, 217 fixed, and an October scanner that emails maintainers fully model-generated reports with no human review. curl's …

An executable synthetic test for a subtle failure in AI-agent review evidence. Two AI agents can...

PHP2Shell, Node2Shell, LiteLLM, and Shai-Hulud expose gaps in software trust. Apply five SIP controls to reduce exposure and contain damage.

Your agent system does not learn. It just runs. Most multi-agent systems I see have the...

SLayer Text to SQL fails quietly. The model guesses a join, invents a revenue definition,...

An anonymous poll, a debate about multimodal testing, and some uncomfortable questions about who...

Wiring a tool takes an afternoon. Running it for real users doesn't. Getting a model to...

Measuring authentic student performance in capstone projects with a mobile 720p demo studio, 2-stage diarization, and fake-log auditing using Gemini 4.

At Sharkly, people rarely fix routine bugs by hand. Most bugs go directly to an AI agent. Sharkly is...

Most online image editors follow the same pattern. You pick a file, the browser uploads it, a server...

A lot of engineering work starts the same way: someone drops a message in Slack. "The export button...

This is Part 5 of a series building an HL7 v2 to FHIR R4 interoperability service in public. The...

An AI agent can stay within its step limit and still exceed an acceptable response time or consume...

Deterministic validation hooks for AI-generated code. Stop type errors, security holes, and test failures before Claude commits them to your repository.

A small laptop is a full build kit. Here's how far mine went. TL;DR: A reader suggested I publish...

NVIDIA's GPU Is Closed Hardware With a Compiler Inside It. Here's What Reverse Engineering...

AI makes it easier to attempt a replacement. The harder question is what the new software still owes...

Small decision models offer a way to handle routine judgments quickly, provided we are clear about...

We have let go of the wheel. The era of agents is here, and we are long past the point of no return....

Picture an internal expense agent. Someone asks whether a flight change fee is reimbursable....

The decision to rewrite For years, rewriting an existing codebase from scratch was...

The work should be easy to verify and continue after the conversation ends. An agent changes the...

In my last post, I wrote about moving Forem’s performance and maintenance work into autonomous loops...

At Glean, we tested a model that does not write text. It only makes decisions. In our tests, it...

At the start of this year, Kent C. Dodds gave a coding agent a link to a GitHub issue he had been...

Most developers working with coding agents still interact with them directly. They open a terminal,...

Do you need to read every line of AI-generated code to trust it? Not necessarily. You need to check...

Whether you’re trying to build a software factory or already running one, you’ve probably heard some...

Set up your development tools in Docker Sandboxes, control network access, and reuse your environment with snapshots and Dockerfile-based templates.

When AI agents write to and read from your database through legitimate API calls, the attack lives in...