AI Intelligence Archive

LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condition: a retrieval-augmented generation server assembles a different set of retrieved chu…

Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service provider. However, running large-scale m…

Disclosure first: I write digline, a small Python library for regression testing LLM applications....

"Does your AI code reviewer read CLAUDE.md?" is the wrong question to ask. Almost any of them will...

The first version of my router failed over on the first error and flapped constantly. The reason...

TL;DR My AI coding agent kept "fixing" things I had broken on purpose — reverting...

AI can generate code faster than ever. That doesn't mean we're shipping correct software...

The developers of Planet of Lana challenged fans to speak Novo Terali. Instead of a simple social shoutout, I built an end-to-end conlang translation engine, voice synthesizer, and quarantine panel.

A tool description reaches the model as instructions. It is written by whoever published the server,...

A Japanese version of this is on Note. RoamSwitch is a network security tool I build solo for Mac...

An independent audit in April 2026 measured roughly a 78% false positive rate from regex-based MCP...

Last week my AWS bill hit $300. I knew there was waste hiding somewhere. Forgotten EBS volumes, idle...

Continuing my thoughts after my previous article, and having too much free time lately, I have been...

Dead Code Is More Dangerous Than Broken Code The opening: an AI confidently told...

Tools like Claude and Cursor can generate a clean component in a couple of seconds. But generating...

I’ve been doing a lot of code reviews recently, and I’ve noticed something about my experience during...

From a founding engineer in a startup: Don't refactor or do more work than needed unless it's...

DeepSeek released its own agent harness this August. It crossed 66k stars in about a day (yes,...

Last month I was on a call with my team lead at BS23, walking him through a change in one of our...

Update — v0.2.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

Ask an AI agent for a discussion-board schema and you'll get one in about four seconds. Here is the...

A IA já escreve código. Muito código. Em poucos meses, "pedir para o agente fazer" virou parte do dia...

This is a reference architecture for bringing AI into a company. It has five layers: users and apps,...

The Problem Is Irreversibility When an AI agent can clone a repository, mine a knowledge...

A full technical walkthrough of automating LLM agent error classification using n8n — webhook ingestion, dedup fingerprinting, Gemini structured output, fix playbook routing, and Slack reporting. Free workflow JSON included.

Every vector database tutorial opens with pip install pinecone and skips the part where you...

Your MCP server's tool schema is the entire interface a model has. No README, no repo, no idea what...

Skybridge v2 adopts the MCP 2026-07-28 revision, replaces the single McpServer with a per-request factory, and ships @skybridge/test so you can assert that a model actually reaches your tools.

Not "AI-assisted." Not "copilot suggestions I edited." I mean I made a rule: for 30 days, I don't...

A page that had already passed five machine gates and a human's signature turned out to cite a source URL that never renders the number it was cited for, because every check compared the fact-check sheet against itself instead of against t…

Ran Qwen 3.8 27B 4-bit quantization benchmarks on RTX 4090 and M-series Mac for local AI agents. Don't fall for 1-bit — here's why.

Six months ago, Aiden was much closer to a hardware experiment than an Agent platform. The first...

I fine-tuned a small language model to sort messages into safe or unsafe, the kind of check a...

Inside SFPU Overflow Bugs: How a 40-Year-Old Rounding Trick Breaks on Modern AI...

I am building Postrai, an AI flyer generator for small businesses. The problem I kept seeing was...

MTP (Multi-Token Prediction) is a technique that lets a language model predict several tokens ahead...

Test whether an AI agent guardrail is still working: rerun the corpus with the gate deleted. Each bad input lands LOAD_BEARING, SHADOWED or MISSED.

Most voice-agent demos have a simple loop: The user speaks. The model thinks. The agent...

Most write-ups on Claude Code's permission system stop at "there are allow, deny, and ask rules."...

Decide to become an AI engineer and the first thing you meet is a framework list. Learn LangChain?...