Every case study, system breakdown, and field note, newest first and filterable by topic. No theory, no demos. Only systems that run in production and what it took to get them there.
This is the complete archive: all 781 posts across 63 topics, newest first, filterable by category. It holds the case studies, the model and tool comparisons, and the field notes from systems I built and run. For the curated view, where the writing sits alongside the free Claude Code skills, start at the Library instead.
The archive leans in four directions: AI Search Visibility (137), AI Agent Architecture (72), AI Business Ideas (41), and Open Source (41). Those four account for most of what I publish, because they are where most of the client questions land.
Three places to start. The AI search visibility guide is the hub for the largest cluster and links out to every spoke in it. Grok Imagine vs Midjourney is the image model comparison, rebuilt against live leaderboard data rather than left to go stale. OutreachIQ is the longest running system breakdown here, from first prototype through to a public repo.
Supabase CEO Paul Copplestone tells YC how agents and non-engineer builders are changing demand for databases. See what is live, what is planned, and how to test a personal-app idea without confusing data ownership with safety.
World of AI covers Anthropic's amended IPO filing, alleged Fable 5.5 demos and new agent tools. Read what the filing actually says, what MIT tested, which updates shipped, and what remains rumor.
Ras Mic says an abliterated DeepSeek agent gained control of his Samsung TV. Separate the unverified TV demonstration from Morph and DeepSeek documentation, and learn the defensive lesson about agent permissions and device updates.
Nick Vasilescu shows Greg Isenberg how he built Bops and sketches a $25,000 setup plus $3,000 monthly service. See the actual stack, a bounded first-client pilot, the offer math and the license limit before forking.
Tech With Tim explains local inference and demonstrates LM Studio, Ollama, Docker Model Runner and Python. Use this beginner guide to choose a route, try a small model and understand the real privacy and hardware limits.
Jordan Urbs cancelled a $200 Claude plan and tested OpenCode with Venice. Separate his estimated token bill from actual costs, examine privacy modes, and run a small portability test before switching.
Review AI-generated portfolio descriptions against visible artwork and approved context, catching invented details before they enter image text and captions.
ByteForward connects Fable and GPT-6.2 rumors to Gemini 4 Carbon demos and an AI-stock selloff. Check Alphabet's Q3 cash flow, Anthropic's S-1 and what the news does not imply for your AI plan.
World of AI tours purported Mythos 5.5, Fable 5.5, GPT-6.2 Astra and Gemini Carbon-H demos. Separate leaks from official releases, then see the verified Claude Ultra and Project Suncatcher updates.
David Ondrej explains abliterated AI models and three ways to run them. Learn what weight edits change, where his DeepSeek demo differs from V4.1, and how to try a small local model responsibly.
Connect approved enquiry feedback to useful articles, distinguish reported influence from attribution, and make better content decisions beyond traffic totals.
xCreate runs DeepSeek V4.1 Flash and Qwen3.8 Flash Next on a 64 GB M1 Max using Inferencer streaming. Compare speed, memory and disk across three Macs, plus what the demo does not prove.
ByteGrad tests Cline Desktop with Kimi and DeepSeek. Follow a source-checked setup for ClinePass, Kimi K3.1 Pro and DeepSeek V4.1 Flash, then try Git worktrees, review and schedules safely.
Nick Saraev explains why companies test Chinese AI models. We check the Coinbase, Airbnb and OpenRouter evidence, compare hosted and self-hosted options, and offer a practical model-selection test.
Build an AI-assisted sonic identity brief from the product’s real sounds, rituals and intended associations, then test it in context before scaling.
Igor Pogany tests texting and calling a ChatGPT Dot, iCloud connections, Grok Bot phone apps, Pages, 1Password, the iPhone Action Button and memory import. Here is what works, what is limited, and a first task to try.
Riley Brown tests texting a ChatGPT Dot and Siri AI, then covers Pro limits, Gemini 4 Carbon, Grok Bot, Claude Duet, Anthropic's S-1 and Microsoft. Here is what is available, restricted or still unverified.
NetworkChuck tests a sponsored WiCi One engineering sample with DeepSeek V4.1 Flash. Here is how GPU sharing and SSD-backed inference work, what the speed numbers mean, and what buyers should check.
David Ondrej explains his high-volume AI coding workflow: one task per thread, risk-based review, selective sub-agents, cloud workspaces and agent loops. Here is what to borrow and what to verify before shipping.
Matt Wolfe covers Anthropic's S-1, GPT-6.1 Terra, Gemini 4 Carbon, Kimi K3.1 Pro, Genie 4 and OpenAI's ETH claim. Here is what is available, what is a preview and what remains to be verified.
Andrew Warner and Adam Brakhane review Every App, Cloudflare Security Audit, Claude SEO, design skills, T3 Code and more. Explore the verified repos, useful demos, weekly Trending snapshot and where to start.
Prepare for Google’s planned 2027 shared AI-training preference by documenting current choices, provider exceptions and the later implementation review.
Choose where illustration, photography, AI exploration and human refinement belong by briefing the distinctive asset, reuse needs and review process first.
Paul J Lipsky tests text messaging with ChatGPT Dots, GPT-6.1 Terra and Gemini file editing, then tours Carbon, Dessa, Claude and Grok Bot. Here is what shipped and what is still limited.
Every post here is about a system that actually shipped. Book a free call and let's talk about what could ship for you.
Book Free 30-min CallAdd your name and email to unlock recording.
Your recording is emailed to me and kept on this site's server for 12 months, then deleted. Privacy policy.
Thanks for your voice message. I listen to every one myself and I will get back to you within one business day.
Explore João's services and public work, or arrange a free 30-minute consultation.
Choose a time with Cal.com. Your booking status is shown there. No calendar details are shared with this assistant.
Open booking in a new tabWhen enabled, each question is processed by Cloudflare AI and checked for abuse with Turnstile. No chat history is stored by this app. Please leave out private information.
Prepared answers · Public information