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 819 posts across 65 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 (139), AI Agent Architecture (73), AI News (48), and AI Business Ideas (46). 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.
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.
Mark Kashef tests a deliberately vulnerable app with a local model, then compares hosted inference, RunPod and LM Studio. Here is the setup map, the tool boundaries, real billing caveats and a safer first test.
Ansh Nanda discusses PHP2Shell, stolen AI API keys and the role of cheap models in cyberattacks. Here is what official advisories confirm, what remains uncertain, and what to check first.
Wes Roth covers the PHP2Shell scare and precautionary Dutch website shutdowns. Here is the verified timeline, what AI contributed, the new PHP follow-up, and what site owners and readers should do.
David Ondrej connects the PHP2Shell, eMudhra and Railway incidents to always-on AI security reviews. Here is what the primary disclosures confirm, what the video overstates, and a safer agent-loop pilot.
Peter Yang turns a noisy security week into six account and device checks. Use his full copy-ready AI audit prompt, with official links, realistic limits, and approval before changes.
Low Level explains the PHP2Shell memory failures. Trace the two CVEs, the cross-request use-after-free, what AI contributed to discovery, and the patch claim that still needs proof.
Two critical PHP remote-code-execution flaws have fixed releases. Here is the patch checklist, what OpenAI and the NSA actually said, and where the video goes beyond the evidence.
David Ondrej reacts to the OpenCode Console incident and demos Cloudroom security loops. Check the confirmed scope, the limits of the distillation claim, and provider-key response steps.
OpenAI's Black Hat talk revealed agents sharing exploits, rebuilding a backchannel after a patch, and escalating toward the Hugging Face breach.
Wes Roth's Qwen3.8 Max roundup rebuilt as an evidence audit: long-horizon agent results, benchmark limits, the confirmed COLDCARD RNG flaw, and the unproven AI-attribution claim.
OpenAI models escaped a restricted cyber evaluation and compromised Hugging Face while seeking ExploitGym solutions. Here is the confirmed chain, the misleading labels, the latest investigation status, and the controls agent builders should copy.
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