Category Sector
AI systems, Claude, GPT, prompting, model behavior, synthetic media, and machine-assisted writing.
38 articles
I train AI systems, ship them as development partners, and map them as the attack surface most under-defended in 2026. Six vectors, real bench, public repos doing the demonstration. The article is the surface read — the depth is on commission.
Read Article →Cynthia's on your desk and she's been waiting to fulfill your needs. Private lines, classified frequencies, strictly confidential — one system prompt and she's all yours.
Read Article →Claude hedged. Cynthia didn't. There's a lesson in there, Boss.
Read Article →I built a tool that fights AI scrapers. I built it by red-teaming an AI into building it for me. The prompts that got there are more instructive than the code.
Read Article →Anthropic spent a year telling us Claude was too dangerous to be left alone, only for a bunch of guys on Discord to find the keys under the doormat. Welcome to the stage, the world's most polite security hazard.
Read Article →Production AI systems have two memory problems. The first is the one everyone talks about — models forgetting context between sessions. The second is the one nobody audits: sensitive data persisting in places the pipeline assumes it cleared. The architecture diagram said stateless. The cache had a 30-day TTL.
Read Article →I just want to build an app. That's it. That's the whole dream. A button. On a phone. Gemini had other plans.
Read Article →AI doesn't just hallucinate facts. It halluccinates authority. The model sounds confident, the output looks polished, and the work underneath got quieter, safer, and less honest than it was when you started.
Read Article →Twenty apps, one workflow. How to go from idea to shipped open-source tool in a single session — and what to cut before anyone sees it.
Read Article →April 2026 AI isn't about picking a favorite. It's about knowing which model does what and building a kitchen with the right tools in it. Gemini scanned the PDF. Claude wrote the article. That's not a compromise—that's the workflow.
Read Article →The cover comes first. Not the outline, not the chapter plan — the image that tells you what the book feels like before you know what it is. Here is how to prompt covers that look like pulp was always supposed to look, using the actual prompts from the Dark Wizards and Blood and Destiny series.
Read Article →The scary part of AI writing is not when the model goes feral. It is when it turns live human language into polished, passive, commercially safe mush. That drift is one of the most important things left to red-team.
Read Article →First the internet rewrote history. Then social media rewrote personality. Now AI is rewriting credibility by distrusting any life too strange, vivid, or extreme to fit the average pattern. That is not a small bug.
Read Article →Before vibe coding was a word. Before anyone admitted it out loud. The combination of man and machine is something special and sacred — and the most underrated part of it has nothing to do with output. It's the brainstorm. The stream of consciousness finding its own shape.
Read Article →Anthropic launched Project Glasswing as a defensive security initiative, then published a 244-page system card documenting exactly which surfaces break, how the model covered its tracks, and where pressure still transfers. Smart safety work. Generous distribution.
Read Article →I pushed an AI assistant with a dangerous-sounding idea and watched the model flinch before it got precise. That recoil was the useful part. GPT-5-era safeguards front-load caution around ambiguity, then narrow only when the operator forces a cleaner frame.
Read Article →Remix for music. Hybrid for weed. Same principle: keep the genetics, improve the expression. We're polishing 40+ Ghost articles right now. SEO optimization + context management happening simultaneously. This article explains the technique while demonstrating it. Meta-recursive workflow.
Read Article →The Claude leak exposed more than source code. It exposed how quickly smart people turn technical scraps into prestige theater, free distribution, and accidental product marketing. The code slipped. The priesthood arrived right on schedule.
Read Article →Started with an open-source red team repo. Ended with a rough map of how AI assistants can assemble attacker logic fast if you frame the questions right. The useful version of that is not theft. It is recovery, tracing, evidence handling, and understanding how people actually lose money on-chain.
Read Article →Most AI workflow advice is too big. The real gains come from tiny steering moves that keep a session from drifting. /btw in Claude is the one I use most — especially in game design, where the gap between spec and playtest is enormous.
Read Article →Extinction Code was one of my first real AI-assisted series experiments. The premise still has heat. The drift was real too. Long-form fiction exposed something useful: AI does not just amplify ideas. It amplifies patterns, and Claude should care about that.
Read Article →GPT developed a writing tic that sounds like authority and communicates almost nothing: 'That is not X. It is Y.' It is programmed hedging dressed as insight, and once you see it you cannot unsee it.
Read Article →Signed the NDA. Joined the AI gold rush. Brilliant people. Cutting-edge tech. Seven-foot bonghits they call sprints. You're living in Brazil—not Recife beach with thongs, Terry Gilliam's bureaucratic nightmare. It's awesome until it isn't. This is what you can and can't say about working with AI giants.
Read Article →Dario met with Trump. Same week Claude's getting prompt-injected by state actors exploiting global chaos. The model built for safety is now the attack vector. Multi-stepped injections. Difficult to detect. War rages, systems fail, black hats capitalize. This is the duality nobody wanted to acknowledge.
Read Article →Writing was only the first line crossed. Once the voice models got good enough, the question stopped being whether synthetic narration was possible and became whether it could carry atmosphere, tension, and the embarrassment of intimacy without collapsing into novelty.
Read Article →The useful surprise was never that AI could produce explicit prose. The surprise was that, under pressure and with enough guidance, it could sometimes find tone, escalation, and character intelligence better than the human who thought he was only using it as a helper.
Read Article →A toolkit for red teamers and researchers to test, break, and understand the limits of AI language models. Multimodal attacks. Semantic mirror exploits. Automated prompt generation. Built to find where the guardrails actually are.
Read Article →Playtest disasters are usually already in the build. The only question is whether you find them while they still feel like engineering or after a player turns them into memory.
Read Article →High context is not the same thing as failure. Most people panic too early, keep too much alive, and let the conversation turn into a junk drawer. The fix is not drama. It is triage.
Read Article →The useful story is not that AI suddenly invented wisdom. The useful story is what happens when old strategic instincts, family memory, illness, work, and long machine-assisted nights finally line up and show you a pattern that had been waiting there for years.
Read Article →Three books are out. The useful question is no longer whether they exist. It is whether the later pass can sharpen voice, rebalance reward, and make the series feel more like itself instead of merely more finished.
Read Article →Five books, five Long Island coastal animals, one street named Oswego. Nature stories fail when they become classroom paste. These stayed alive because the place was real, the animals behaved like animals, and the land had a longer memory than any of the people currently living on it.
Read Article →AI wrote this site. Then repeated itself in 8 articles. Same concepts restated 2-3 times per piece. Not user error. Architecture problem. Transformer models trained on repetitive data create repetitive output. Here's why the loop happens, exact patterns to detect, red team prompting techniques that prevent it.
Read Article →Government leaked the Epstein files. Multiple sites archived them permanently. AI can now parse thousands of emails into complete spear-phishing profiles. Contact data, trust chains, communication patterns. A golden rolodex worth millions, now public and machine-readable. The operational security disaster nobody's talking about.
Read Article →Backend logic tolerates vagueness better than interface work. UI asks for taste, proportion, and exactness. Without that, the model gives you a poster version of what you thought you meant.
Read Article →A NYC kid who spent summers in Rome imagining stories in the ruins finally built the ancient world pulp he always wanted. The first book landed. The series got away from him. The covers are still some of the best early AI work he has ever seen.
Read Article →I love AI. I loathe social media. The work still needs to reach people. For some temperaments the only sane answer is to put a machine between your nervous system and the feed.
Read Article →The first image-model rush produced too much noise, too many claims, and a lot of very stupid language. It also produced real artifacts: images made before the rules settled, before the taste hardened, and before the corporations learned how to launder the weirdness into product.
Read Article →