Most people have no idea how to write a viral Twitter thread. I’ve studied thousands of high-performing posts. Here’s the exact formula 👇 1️⃣ Start with mild condescension Position yourself as someone who understands a truth others don’t.

You're doing it wrong

facebook killed real communities

the fastest way to vibe code is wiring the foot pads up to your agents "ok" button.

Does it run on Sativa?

Turns out @cursor_ai can also help with lunch.

Prompts are the incantations of the digital age, summoning perfection, or desolation, based on how your spells are cast

RIP Debian. Without meritocracy, we fall into mediocrity. Those who gain power through dubious means while expousing any platitude to eliminate competition rarely result in the quality of leadership needed to breed success within the team.

Dad's tape measure. He's been looking for it since 1997.

I just read how Anthropic's own engineers actually use Claude internally. They don't prompt engineer. They context engineer. And the difference broke my brain. Most people are still obsessing over the perfect phrasing. The magic sentence that makes Claude finally understand them. That's not the problem. The problem is what you're putting around the prompt. Here's what Anthropic's own team actually does: → Just-in-time retrieval Don't load everything upfront. Pull data dynamically using tools when the model actually needs it. Claude Code does this brilliantly. It uses grep, head, and tail to analyze codebases without ever loading full files into context. The model stays sharp because it's never drowning. → Compaction When you hit context limits, summarize the conversation. Keep architectural decisions. Discard redundant tool outputs. Maintain continuity without the bloat. Most people just start a new chat. That's not the fix. Smart compression is. → Structured note-taking Have the model write persistent notes outside the context window. Pull them back only when needed. Think of it as your AI keeping its own NOTES.md file. It remembers what matters without wasting attention on what doesn't. → Sub-agent architectures Specialized agents handle focused tasks and return compressed 2k token summaries instead of raw 50k token explorations. Separation of concerns at the AI level. Same principle that makes engineering teams work. Here's why this matters: LLMs have an attention budget. The transformer architecture creates n² relationships between tokens. Every token you add depletes focus exponentially. Stuffing your AI with information isn't thoroughness. It's noise. Anthropic calls the result "context rot." More context, worse performance. The relationship is real and it compounds fast. The shift in thinking is everything: Before: "How do I write the perfect prompt?" After: "What's the minimal high-signal context that drives my desired outcome?" The best AI engineers aren't prompt wizards anymore. They're context architects.

Only the lazy and ignorant blame technology for their lack of productivity.

Coding with AI is like Bush's invasion of Iraq. Tempting to claim early victory once superior tech reaches the objective. It's wiser to anticipate a long patrol, IEDs, shifting ROE and a never ending battle of hearts and minds. Could be worse. Could've been Afghanistan.

New side project 🤠 Self-hosted AI for nightly reviews, bug scans & security probes of all my repos, with cross-repo Deepwiki functionality. 🧠 This should simplify repo ecosystem alignments & pattern consistency 🤓 A free AI, for judging the output of paid AI.

Don't use it to replace your brain, just to make your ideas faster to implement.

On the upside, there's a boom in QA.