AI Intelligence Archive

I build Compresso, a local AI compression layer, using different techniques like Headroom, Rtk and...

How to build a production-grade drafting agent on local SLMs (Llama 3.2 3B) using deterministic Python verification, tri-state guardrails, QWK-calibrated evals, and continuous few-shot learning.

I had my own infrastructure context server running behind my editor, the way I do every day, and...

I've been writing Android for thirteen years. For the last two of them, a large share of the code...

This is a submission for Weekend Challenge: Generosity Edition What I Built Every...

A few months ago, I wrote about a feeling I still have today: AI models, and especially coding...

How I built HealthMitra, a Hindi/English voice agent for India's health-access gap, on LiveKit and Murf Falcon — plus three real bugs it took to get the multi-agent handoffs working.

Claude Code writes every session to ~/.claude/projects as JSONL. I wanted to know what I'd actually...

We measured whether AI-written code is messier than human-written code, across 500 real bugs where a...

Update — v0.1.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

The first version of an agent usually has one place for context: the prompt. The user request goes...

A practical guide to wiring up an MCP server on SAP BTP Cloud Foundry so that an LLM agent's requests reach your on-premise ABAP system under the calling user's identity, not a shared service account.

📖 Originally published on meridianbuild.dev my engineering blog documenting the real bugs and...

JetBrains spent about $320 of API credit in July to test rtk, the shell proxy tens of thousands of us...

Headline: pgvector is a Postgres extension that adds vector column types and...

This is a submission for Weekend Challenge: Generosity Edition What I Built Anyone who...

"Please be careful" is not a security control An agent at a Fortune 500 financial services...

The moment I stopped trusting the agent I built a trading agent. It worked in backtests. Clean...

I build Connexa, a chat product for cross-language teams: you write Chinese, your teammate reads...

AI agents already answer questions about small businesses. Most of the time they do it from stale...

My review agent turned a 1,000-line feature into 4,000 lines by flagging attacks that could never happen. One required field in every finding fixed it.

What if your backend wasn't just built for humans and services — but for AI agents too? That's the...

Yash K Saini — Engineer, building in public — AI/ML, low-level (Rust/C/C++), and open source. GitHub...

We’re entering an era where producing code is becoming easier. Understanding what we produce may be...

This month a developer ran a working language model on a Sony PSP-2000. That is a 333 MHz MIPS...

I've released vincent v0.8.0, and this release pushes the project much further toward the workflow...

I've spent about 700 hours in Claude Code over the last year, building a personal AI assistant that...

I've been reading through dev communities lately, and this exact topic keeps showing up in different...

Every week someone asks a version of the same question: "How much will this actually cost me per...

I went looking for a better runtime check and found a different way to think about the problem. I...

0. What I studied and what I found I studied nano-vLLM as a small LLM serving engine:...

Submission for the Cloud Run AI Challenge — #AccelerateAIwithCloudRun When I started this challenge,...

The first time I seriously doubted the framework was not because the model hallucinated. It was...

AI agents don’t use web browsers. They don’t click buttons, submit forms, or trigger standard HTTP...

The first version of a RAG system always looks convincing. You connect a document loader, a vector...

The first version of most AI features is not a system. It is one giant prompt doing too many...

Your Laravel app adds an agent. The controller action looks harmless: one user message, one model...

We paid for a vector database for a year. It was faster than Postgres at the one thing it does. We...

The tenth prompt tweak usually feels like progress. The eleventh reveals the problem: the fix that...

The tenth prompt tweak usually feels like progress. The eleventh reveals the problem: the fix that...