Kevin has earned my follow. A philosopher-poet of our time.

I notice a lot of people are struggling to conceptualize Jev and where it fits in with current LLMs. In short its filling an important gap, not replacing LLM's 👇 It helps to look at how we think. When you open a support ticket, you don’t carefully reason through everything from scratch. You notice things immediately. The customer sounds angry. This looks like a billing problem. The request seems routine, but something about it needs a second look. You’ve made several judgments before you’ve decided what to say. Those judgments guide your attention. They let you move quickly through familiar situations and slow down when something needs thought. In LLM agents, we often ask the same model to do all of that: assess the situation, reason through it, choose an action, and write the response. Jev gives us a way to divide that work. Give it messy context and specific, typed questions, and it returns decisions, probabilities, and confidence in about 100ms. An agent can use those results to act on a routine case, bring in an LLM for deeper reasoning, or ask a human for help. Together, Jev and an LLM can form a system with something resembling the interplay between quick judgment and deliberate thought. The rough analogy is System 1 and System 2. Our thinking depends on both, and on knowing when a first impression deserves closer attention. That’s what makes the AGI argument interesting to me. We’re starting to build systems where different kinds of processing work together and help determine when each is needed. It’s still a loose comparison to human cognition. Fast decisions plus an LLM don’t establish general intelligence. But they give us a closer approximation of how we actually work: notice, judge, act, and think harder when the situation calls for it.

Astra sucks for long running /goal work. It gets in the weeds in a sort of perfectionist spiral and loses the big picture. Then it builds you a perfect "something" that's nothing like what you first set out for it to build. It's also really good at burning a $200 Codex plan in 24 hours doing these spirals. Still trying to figure out where it fits in my workflow. For now it needs HITL at gated steps to be useful. Anyone else hitting this, or is it just how I'm running it?

Here is the link. The key difference here is the philosophy that we should not be aiming for zero human companies (paperclip) right now. Single human companies are the practical target. tmacc.github.io/org-as-repo/

i just listed leafari.app on outliked, the leaderboard where you participate by posting and win based on likes. every like on this tweet pushes it closer to #1. do your thing 💗 outlike.lol/?via=leafari.app

Well, I placed a top bid on an outbid .lol inspired site for mobile apps as an experiment. Let’s see if any downloads come from being #1 on bidyourapp .com… @heysatya_

Building is now easier. Building something intuitive, beautiful and joyful to use still takes real skill. It takes taste, vision and customer empathy. Design and thoughtful product planning set you apart.

The irony of the coldcard breach is that the open source code which many thought was a security feature turned out to be an open door for AI to find its weakness. Obscurity is a layer of security, especially in the age of AI.

I needed something to redzone my Claude Code subscription, so I’m building an MMO. I’ve been looking for a project ambitious enough to truly stress-test my Claude Code Max subscription. As a longtime RPG fan with nostalgia for the old text-based MUD days, and with an itch to build a game, I decided to skip graphics entirely and focus purely on systems, mechanics, and world design that make a living world feel real. That’s what I’m doing now, and the design space we’ve reached is one of the most fascinating things I’ve ever worked on. Around the same time I started this, pure LLM-based generative games were getting buzz again. AI Dungeon had its explosion years ago, and now there’s a new wave of “AI game” startups. But every time I tried one, it felt loose—too much freedom, no grounding. Choices didn’t matter because nothing persisted underneath. The AI just vibed and generated something that sounded right but meant nothing. Characters forgot their names. The world forgot yesterday. It felt like a gimmick: impressive tech demo, not a game. That led to a better question: what would good game design look like if it actually integrated LLMs’ generative strengths with the deterministic, shared experience of a multiplayer world? Not AI doing everything, not AI as a bolted-on coat of paint, but an architecture built around what AI is genuinely good at and what it absolutely cannot do. That’s how The Unwritten began. What it is A text-based MMORPG. Persistent shared world. Permadeath. Dynasty system. A magic system grounded in theoretical physics. A frontier that literally doesn’t exist until players walk into it. The world exists in three layers: - Deterministic layer (bottom): The Athenaeum (think Oxford crossed with the Library of Alexandria) and the Seven Cities are hand-crafted and canonical. When I say “meet me at the Forum,” everyone knows exactly where that is. This gives shared reality, weight, and stakes. - Procedural layer (middle): Consistent, learnable rules and systems. The magic works the same way every time, can be taught, documented on a wiki, and remains fair and predictable. - Generative layer (top): The frontier. When you step beyond the known world, the AI generates terrain, ruins, creatures, NPCs, and mysteries—all shaped by lore and constrained by procedural rules. Crucially, once discovered, it crystallizes into the permanent world. Every player after you will find that ruin. Your name is etched as the discoverer. Forever. The unknown becomes the known. That’s the core loop. The magic system Reality is woven from the Threads of the Utterance—strings (as in string theory) still vibrating from the Creator’s First Word. Everything differs only in frequency. A stone wall and the air beside it are the same substance singing different songs. No spell slots, no mana, no cooldowns. Only knowledge—and the cost of being wrong. Four disciplines, each rooted in real physics/philosophy: - Sonaecraft (String Theory): Every material has a unique Tone. Transmutation requires walking harmonic bridges through stable intermediate tones (A* pathfinding on a tone graph). Wiki-documentable, tradable knowledge. Cost: Harmonic Contamination—your own Thread drifts toward the studied frequency. Masters become visibly marked: metallic skin, vibrating eyes, echoing voices. - Attestation (Quantum Mechanics): Before observation, things exist in Fieri (superposition). Practitioners can delay collapse and bias outcomes. More observers = heavier Gravitas (decoherence), so Attestors are stronger alone and weaker in crowds. Cost: Fieri Drift—prolonged superposition blurs identity until you fade into ambient background. - Codex Arts (Simulation Theory): Reality is information; practitioners read and edit the Codex (source code). Integrity checks make consistent edits cheaper and contradictory ones dangerous. Exploit path: Logic Bombs that trigger localized Excessus (buffer overflows) for impossible writes. Cost: Data Overflow—overexposure causes cognitive fugue; long-term users lose the ability to process normal input. - Nominatio (Logos Theology): True Names must be earned through personal experience and interaction (LLM-generated unique paths). Comprehension is 0–100% via Insights. At 100%: mutual understanding and co-creation. Effects are consistent and balanced across players. Cost: Name-Sickness—you gradually become the thing you deeply understand. Dynasty system (permadeath that matters) Characters can die permanently. At zero health you enter a ~5-minute Dying Light window where others can save you. If not, you’re gone. Survive long enough (100+ real days), build legacy, and hit thresholds → establish an heir. Heirs inherit 40% tendency (faster skill learning in mastered disciplines). NPCs remember bloodlines. Dynasties stack generational bonuses. One death without an heir ends the line completely. A Bloodline Registry tracks dynasties, ended lines, and player-written memorials. The emotional weight is real. World design Known world: canonical Athenaeum, Seven Cities (each with distinct identity), connecting roads. Unknown: eight biomes, wilderness up to 50 rooms from landmarks, dungeons 20 levels deep, generated settlements capped at 30 NPCs/15 buildings. Lore explanation: frontier exists in Fieri until observed and collapsed. NPC system Two-layer dialogue: canonical core (fixed, documentable) + expressive LLM variation through personality. Trust tracking, knowledge maps, action parsing. Challenges Balancing the tone graph, Gravitas edge cases, Codex integrity/exploit design, crystallization quality threshold, and dynasty emotional clarity. Why it matters Most AI-in-games answers are weak: full AI (meaningless after an hour) or AI as texture (same game, prettier wallpaper). The interesting path is architectural: deterministic foundations for trust and stakes, procedural rules for fairness and depth, generative AI for emergence and personalization—each doing what it’s best at. Discoveries persist. Choices ripple across players. Knowledge is literally power. We’re still building, but the design space is the most compelling I’ve touched in years. If you played MUDs back in the day and this resonates, that’s exactly the feeling we’re chasing. Looking for playtesters—comment or DM and I’ll send an invite.

CLI is the ui for agents to interact with your application. It’s time to put as much effort into a CLI for your api as you do into your browser UI.

I was only several prompts away from a major breakthrough on my project with claude code... API Error: 500

Claude code is down. I'm going to give codex a spin... for the first time.

This. On its own, it’s cool and worth discussing, but the hype and froth has left planet reality for OpenClaw.