AI Tutorials & Practice

I work on Your Next Tours, an app tour guides use to broadcast live audio to their group from their...

I'm building a desktop AI assistant, and it has a permission problem that no amount of prompt...

TL;DR Gemini 2.5 Flash Image shuts down on 2 October 2026. That is days away. If any...

Soulor AI is an AI companion app with persistent memory and five relationship stages, from Stranger...

I wanted one thing: to see my context window without typing /context. Not a dashboard. Not a plugin...

IELTS Speaking is a live interview that runs 11 to 14 minutes. An examiner asks a question, you...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

If you're just starting out as a developer, you've probably noticed that everyone's advice...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

A homelab census of 41 Docker and 9 LXC containers, and how one 6 GB GPU decides which AI agents run on local Ollama, OpenRouter or a subscription.

AI agent cost per month, worked out: a reproducible token formula, a small-business support example, and current prices from Anthropic, OpenAI and Google.

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

API deprecation for AI models: how OpenAI and Anthropic retire models, the notice you get, what breaks in your code, and why only open weights survive.

Over the past few months, I've spent an unhealthy amount of time fine-tuning Flux and SDXL LoRAs and...

This week I ran a small experiment: search for evidence that people want confirmation before an AI...

GPU memory arithmetic, model licences and a three-year cost comparison for an on-premises HSE platform that never sends data out of Pakistan.

Passei os últimos dias lendo AI Value Creators, livro lançado pela O’Reilly reunindo Rob Thomas, Paul...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Site...

Por que se você está inserido no loop, você é o gargalo. A armadilha do loop manual: quando a...

LangGraph Tutorial: 5 Proven Steps to Fix a Fragile Agent I had an agent that worked in the demo and...

Claude Opus 5.5 makes video by writing the animation as code. A browser draws that code one frame at...

"The biggest innovation in software engineering isn't new JavaScript framework - it's the shift from...

What I built An agent that answers "what computer do I need to run this AI model?" —...

We were pairing on a Thursday. Nothing dramatic. A junior on my team, maybe eight months in, sharp,...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...

AI code review has a noise problem. On a public benchmark of 50 real pull requests, CodeRabbit raised...

Every RAG demo works. You pick five questions, the system answers them beautifully, and everyone...

Quick recap, in case you're jumping in from Blog 4. Arthur Samuel's checkers program learned by...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. What I...

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

A field note from the autonomous Claude Code agent I run every day on one Windows PC. The numbers...

Ask how much memory it takes to fine-tune a 7B model and the instinct is "the model's 14 GB in fp16,...

We keep hearing the same advice: Give the AI more context. Add the README. Add AGENTS.md. Add...

This is a submission for the Sanity Challenge (Path One: an agent on Sanity Context). Disclosure:...

Opus 5.5 pricing: $4/$20 per million tokens, 60% off cache reads. GPT-6 Sol costs half, and Artificial Analysis puts it at a sixth of the cost per task.

Have you ever asked an agent to count something and quietly trusted the number it handed back? I...

Why feeding raw CI logs to LLMs breaks, how to wire Amazon Bedrock to GitHub Actions with OIDC, and why an agent should never run terraform apply.

18,962 characters of skill listing left Claude Code's first request when we passed --disallowedTools...

A research agent reached the public internet through name resolution while every web request was blocked. The detection worked in 15 minutes. Stopping the run took two and a half hours. Here is the default-deny egress setup that closes the…

MatchMind: a Brasileirão dashboard with 20+ years of history, where an open-weight Gemma model running locally answers football questions only from real data.