One Site’s Google AI Opt-Out Test Estimated 23% of Search Clicks Came From AI Features
Google does not provide publishers with a separate click total for AI Overviews or AI Mode. That...
Tutorials
Benchmark scores say nothing about whether the release runs
On Nov 8 I went through a fresh speech-model release the way most people in that scene go through...
Reasoning models think in silence. Our job queue read silence as death.
One morning, our daily automated code review flagged a refactor we had just pushed. The finding fit...
Why JSON tool calling is breaking your agents (and how MCP Code Mode fixes it)
Standard tool calling looks great when your agent has three tools. You pass the JSON schemas in the...
Connecting Business AI Agents to Existing Systems: An Ontology-Inspired Prototype
Access to business data, and safe ways for agents to use it, receive a lot of attention. From my own...
What 84,800 local spans taught me about my coding agents and my local AI services
Token trackers tell you what your agents cost. They do not tell you why a child agent hung for ten minutes.
I dumped semantic i18n keys. Now the source text itself is the key — and LLMs do the rest.
The thing everyone does (and why we stopped) If you've ever built a non-trivial UI in a...
I built an AI field guide that works with the internet off, live on stream
This is a submission for the Hacktoberfest 2026 DEV Challenge, Week 3: Slow and Steady. ...
My On-Call Agent Stopped Suggesting the Fix That Already Failed
Last time our database pool ran dry, an AI assistant told me to increase the connection pool. We had...
ChatGPT Desktop forwards your SSH agent to the machines its agent runs on: your keys, its repos
The codex app-server inside ChatGPT Desktop ships a --forward-ssh-agent feature: your local SSH agent is shared into the agent's execution environment via a stable socket, so agent...
How I built long-conversation compaction for my desktop AI companion: at 36 messages, old turns become one 2,000-byte recap
Ankita AI is a desktop AI assistant by Krish Verma, and it has a memory problem every long chat hits:...
I put my cat in a Tiny Desk concert, and Cloudflare billed me for a container that wouldn't die
You've probably seen the clip. Charlie Wilson at the NPR Tiny Desk, singing "Outstanding", the camera...
Beyond RAG: The Evolution of AI Knowledge & Memory : From LLMs to Vectorless RAG, LLM Wiki, and Memory
So recently I have been learning a lot about AI systems and architecture and how to build scalable AI...
Your LLM returned valid JSON. That doesn't mean it's telling the truth.
What building an automotive telemetry application taught me about structured output, evidence...
AI Fatigue? I Counted: 9 of the Last 10 Articles I Opened Were About AI. So I Wrote About a Button Instead.
When did every article on the internet become about AI? Last night, in my hostel room, with a cup of...
We ran a launch check on 312 AI-built apps. Most of what's missing isn't code.
Most studies of vibe coding look at the code: how many vulnerabilities, how much technical debt. We...
The AI Didn't Break In. It Knocked on Every Door: What the BOSSAI Mesh Actually Tells Us
For twelve days this summer, researchers at Acronis's Threat Research Unit watched a single person...
My MCP server's confirm: true flag was written by the model. So I moved the approval to the user.
AI note: the code change and this post were written with an AI agent. Every test and output quoted...
The Shadow Backlog: How Agentic Code Generation Overwhelms System Architecture
The Shadow Backlog: How Agentic Code Generation Overwhelms System Architecture TLDR:...
Prime Agent: an open source coding and research agent for long-running work
Prime Agent (Prime Intellect) The agent that writes code should not be the one that judges...
Designing a Backend That Can Be Used by Both Applications and AI Agents
I kept seeing a pattern: a team has a customer account service that works fine. Then an AI agent...
Why Your Coding Agent Agrees With Its Own Bugs: Building cold-jury, a Zero-Dep Cross-CLI Review Gate
Applying Google's Elephant-Goldfish pattern and arXiv:2607.21656 to run sterile, cross-model hostile...
How to Ship a PoC Fast Without Getting Burned Later
Most PoC pain comes from a demo quietly becoming production. Seven rules for moving fast, and how to decide whether to stop, rebuild or harden it.
Automating Support with AI: From a User's Question to a Response
How to assemble context for an LLM, handle its response, and decide when to call another model or a human agent. Part one of a series on automating support with AI.