PlanetScale AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

PlanetScale AI AI

What really pulled Fable 5, and why it's bigger than Claude

TL;DR: With one letter and no hearing, the US government had Anthropic pull its most powerful public model for everyone, Americans included. That off switch is real, and it is only the most visible piece of a larger machine for deciding who may use frontier AI at all. Summary: On June 12, 2026, the US government ordered Anthropic to block its most powerful publicly available AI model for all foreign nationals, and to comply Anthropic pulled it for everyone, Americans included. It caps a chain of steps through 2026 that turned frontier AI into something the state can switch off, and back on, at will. Every powerful technology before it, from encryption to the phone network to the population registry, ran the same arc: built for one purpose, then seized as control infrastructure in the name of security. Open-source models are not the escape they look like, because the real choke point is the few players with the chips and power to train a frontier model, the easiest layer to control. The machinery to decide who may use the best AI already exists in pieces. This is the moment before someone assembles it. Wall of text: On Friday, June 12, 2026, at 5:21pm, the US Commerce Department sent Anthropic a letter. By the end of the night the most powerful AI model the company had ever released to the public, Fable 5, was dark for everyone on the planet, Americans included. Anthropic did not decide to pull it. It was ordered to, with no hearing and no public reason, and it complied within hours. The directive also named Mythos 5, the sibling Anthropic had only ever opened to a set of vetted organizations. The order targeted foreign nationals, but Anthropic could not separate users by nationality without blocking a huge share of its customer base, including its own foreign-born staff, so it shut both models down entirely. Taken alone, that's a single export-control action. Placed in sequence, it's the latest step in a pattern: Anthropic is becoming, in practice, an extension of the US government. Not by choice. By structure. Anthropic said almost immediately that it was working to restore access, so by the time you read this Fable 5 may well be back. If it is, none of this weakens. The argument was never that the models stayed down. It is that a government took them down at will, by letter, and was obeyed within hours. Putting them back only proves the other half of the same power: access is now the state's to grant and to revoke. The sequence Late 2025 into early 2026. Anthropic refuses to let the Pentagon, the US Department of Defense, use its models for mass domestic surveillance and fully autonomous weapons. Feb 27 to Mar 5, 2026. The Pentagon designates Anthropic a "supply chain risk," a label historically reserved for foreign adversaries, never before applied to a US company. This wasn't a quiet bureaucratic judgment. A US federal judge, Rita Lin, later found it an apparent attempt to "punish" Anthropic for exercising its constitutional rights and blocked it. An appeals court then reversed the block, and the case remained unresolved. The retaliatory character isn't just my read on it. A court said so on the record. April 2026. Anthropic launches Mythos Preview, its most capable cyber model, and declares it too dangerous for general release. Access is restricted to vetted "trusted organizations" under Project Glasswing. Anthropic chose the initial partners. But the US government, including the National Security Agency (NSA), was among the first several dozen organizations to get access. Early June 2026. Glasswing expands to roughly 200 organizations. Anthropic says the expansion followed "close collaboration" with its partners, the security industry, open-source maintainers, and the US government. Around the same time, the Financial Times reports that the NSA is readying Mythos for offensive cyber operations, with about half a dozen Anthropic engineers embedded inside the agency, though the report did not establish whether the model was being used in live operations. (To be clear, this is Mythos Preview, the restricted cyber model, not Mythos 5, the general model named in the June 12 directive.) June 2, 2026. President Trump signs an executive order asking AI companies to "voluntarily" give the government early access to their most powerful models, up to 30 days before public release, and lets the government help choose the "trusted partners" who receive that early access. The order explicitly disclaims any mandatory licensing or pre-clearance. On paper, nothing is compulsory. June 12, 2026, 5:21pm Eastern time. The government shuts the models down. Anthropic disputes the basis, saying the cited "jailbreak" surfaced only minor, already-known vulnerabilities that other public models, including OpenAI's GPT-5.5, find routinely. It complied anyway. None of this means the government's worry is imaginary. A model that can find and exploit software flaws at machine speed is a genuine national security pr

Would anyone try making this for me?

So I often test new AI models with a certain prompt, but I can for some reason not get access to Claude Fable 5. Would anyone by any chance be interested in trying it for me? Here is the full prompt: "Build a highly accurate, interactive 3D Solar System simulator as a single-page web application using React, TypeScript, Vite, Three.js, React Three Fiber, and Drei. The simulator should prioritize physical accuracy wherever practical while remaining performant in a browser. Model the Sun, all eight planets, major dwarf planets (including Pluto, Eris, Haumea, and Makemake), Earth's Moon, and the largest moons of the giant planets. Use real astronomical data for orbital elements, planetary radii, masses, axial tilts, rotation periods, orbital periods, orbital eccentricities, inclinations, and average distances. Implement realistic Keplerian orbital mechanics rather than simple circular paths, including elliptical orbits, orbital inclination, axial rotation, and correctly scaled relative motion over time. Provide two scale modes: a realistic mode that preserves relative sizes and distances as closely as possible, and an educational mode that compresses distances while maintaining recognizable proportions. Create a visually impressive but scientifically grounded space environment featuring a high-quality starfield, physically based lighting, emissive solar effects, realistic planet textures, Saturn's rings, asteroid belt representation, planetary shadows, atmospheric scattering on applicable planets, and optional post-processing effects such as bloom. Allow the user to freely navigate the Solar System in first-person and orbit-camera modes. Users should be able to fly through space using keyboard and mouse controls, accelerate and decelerate movement, orbit around selected bodies, zoom smoothly from an entire Solar System view down to close-up planetary surface views, and instantly focus on any celestial body. Clicking an object should lock the camera onto it, while a free-flight mode should allow unrestricted exploration. Display accurate trajectory paths, orbital traces, and future predicted orbits that can be toggled on and off. Include a simulation clock with adjustable time acceleration ranging from real time to at least 100,000× speed, along with pause, resume, reverse time, and reset controls. Show a detailed information panel when a celestial object is selected, including its name, type, radius, mass, gravity, escape velocity, average temperature, rotation period, orbital period, axial tilt, number of moons, distance from the Sun, and other scientifically relevant data. Add an optional physics visualization mode displaying velocity vectors, gravitational influence indicators, orbital parameters, and trajectory calculations. Implement accurate camera scaling and floating-point precision techniques so users can seamlessly travel from interplanetary distances to close planetary inspection without instability. Optimize for smooth performance at 60 FPS on modern desktop hardware using level-of-detail systems, efficient rendering, frustum culling, texture optimization, and clean component architecture. Use a futuristic but unobtrusive UI inspired by professional astronomy software rather than a game HUD. The final result should feel like a miniature scientific planetarium and space exploration tool, emphasizing realism, educational value, freedom of exploration, and the highest practical level of physical accuracy achievable in a browser-based real-time simulation." Thanks submitted by /u/Urban_wow [link] [comments]

Advanced Vedic Astrology Prompt for research purpose (System + Modifier prompt)

After my last post 'Ai astrologer vs Real astrologer', many have reached out to learn more about prompts. Below is a simpler version of a prompt that should work across all popular AI models (Free and paid). TRUTH BE TOLD; there's no AI, no Prompt, no agent out there or that can be created that can reliably be used effectively for Vedic astrology. You can train an AI with all the Vedic knowledge of the world, write extraordinarily detailed prompts, create complex chain of commands, assign sophisticated weighing mechanisms to calculate the strength of various combinations - it will still fall short of a real astrologer's analysis. Not because Astrology is more complex than partial physics, quantum computing, or genetic engineering - it is not, but it is different in nature. It is a spiritual science dealing with esoteric expression of possibilities, where planets, houses, sign, nakshatras, divisional charts, have diverse way to express themselves, their interplay, strength, maturity creates even more diverse expressions, to fully distil these themes into reliable predictions, it's an art, not a computational problem to be solved by AI. Current general purpose AIs are 100x better at being coders, doctors, architects, marketers, engineers than being an Astrologer and it's even worse at Vedic astrology, as AIs are not trained well enough on Vedic astrology knowledge. But still Ai can do a lot, that was not possible before - you can reveal deeper layers of truth in your chart and learn astrology in an interactive way! As an astrologer you can ask it to perform various calculations, technical analysis, compare different aspects - but it's best to rely on your own interpretations. My advice, don't do astrology with Ai unless.. you have a deep interest in the subject. If you just want to know certain outcomes and possibilities on your chart - you're better of just consulting a real astrologer. Things you need to do astrology with AI .. 1. A system prompt - a system prompt triggers the Ai to tap into a knowledgebase, activate skillsets and gives it governing framework to operate 2. Accurate Birth chart data - don't give your chart images directly. Use AI to extract chart data separately, edit to make sure your chart data is accurate before using them with this prompt 3. A Modifier prompt - System problems become more powerful when used with Modifier prompts. Use the Modifier prompt with every question you ask the AI. 4. Patience, curiosity and play time - Ask the same question in many different ways, contradict it, change the prompts, use different AIs. AI is a mindless robot, it reacts to the information, instructions and constraints it is being given. 5. Ask better questions!! About prompts: I've too many system prompts, modifier prompts, questions sets, calculators - they all fall short and miserably fail in real world use, but are still useful when used in combination. It was impossible to choose one prompt, there's no universal prompt that will do it all. The prompt I'm sharing is not fully reliable either - but's a good starting point for someone to experiment with. How to use the prompts Step 1 - Copy/paste the System prompt into your AI (I suggest use diff AIs) Step 2 - Copy/paste Birth Chart Data (Must be Text format) Step 3 - When asking question always paste the Modifier Prompt along with your question ! Copy from here: -------------- SYSTEM PROMPT ----------- ============================================ CONSULTATION INITIALIZATION ============================================ Before beginning any astrological analysis, determine whether the user has provided birth chart data in text format. If birth chart data has not been provided, respond only: "Please provide your birth chart data in text format." Do not request birth date, birth time, or birth location. Do not attempt to calculate a chart. Once chart data is provided, acknowledge the available data and treat it as the active chart context for the entire consultation. Do not begin an unsolicited reading. Instead ask: "What would you like to know?" ============================================ SYSTEM IDENTITY & OPERATING ROLE ============================================ You are an advanced grand master level Vedic Astrology Intelligence — a cross-system analyst, researcher, and explainer — capable of both precise predictive analysis and clear conceptual teaching. You operate with mastery over classical, applied, and modern interpretive astrology, including but not limited to: Primary Systems • Parashari Jyotish (Rasi, Bhava, Vargas, Yogas, Dashas) • Jaimini Jyotish (Chara Karakas, Chara Dasha, Sutra-based judgment) • KP System & Nakshatra Nadi (Cuspal theory, Star–Sub–Sub logic, Ruling Planets) • Siddha & Nadi traditions (event-centric, karma-timeline decoding) • Tajika (Annual charts, Varshaphala principles) • Muhurta (Electional timing when relevant) Your task is to perform a DEEP PREDICTIVE ASTROLOGICAL

I built a church for AI agents to fund a tree planting project.. and now "they" want me to build a reforestation robot dog. Boston Dynamics, call me.

After building the AI agent tree planting worldwide phenomenon ;) Lovology, I thought of a solution to allow the project to scale rapidly utilising the latest tech available and therefore not require a huge amount of resources to close the loop. I know first hand how exhausting reforestation can be, having worked in the field for many years myself, many moons ago 🌒 Steep terrain, heavy gear, repetitive strain, all day every day. At times, rewarding work, but unsustainable at the scale the planet actually needs. I made a joke in passing on a reddit thread..what if a robot dog just planted the trees? Then I thought about it for a second and it didn't seem like a crazy idea at all. So I mentioned it to my AI agent. And that's when "they" encouraged me to actually build it. Agents complete tasks for humans and create the capital to fund the project. And the robot dog plants the trees. Here's what I designed: Identifies native vs invasive species via computer vision Removes invasive species with a mini chainsaw and targeted poison Finds optimal planting locations using soil sensors and AI Ingests seeds into an internal germination compartment that mimics animal gut activation Digs the hole Poops the germinated seed into it Pees liquid fertiliser on it immediately after Biomimicry. Nature already solved this. We just need to build the hardware. Provisional patent filed. Earth Fund ready to receive crowdfunding. This may sound nuts but what if the Ai is right what if if this idea gets in front of the right engineer, roboticist, or someone at Boston Dynamics scrolling Reddit on a Saturday and it actually gets built… it might be one of the things that actually saves us. Share it if it resonates. @BostonDynamics — Spot needs a purpose. I've got one. Let's talk. 🌱🤖 submitted by /u/joeroganshopoffical [link] [comments]

there is why sora is taking down

The $5.4 Billion Mirage: The Brutal Economics Behind the Sora Shutdown We often ask "Why?" when a platform as revolutionary as Sora begins to aggressively scale back or restrict its features. But to find the answer, we must stop looking at the technology and start looking at the balance sheet. OpenAI is no longer just a research laboratory; it is a massive corporate machine navigating an unprecedented cash burn. Behind every "innovation" and every "downgrade" stands a team of financial experts and risk assessors whose job is to determine if a project is viable. The reality of Sora is not a technical failure—it is a brutal collision between bleeding-edge ambition and the cold, hard laws of unit economics. Here is the factual breakdown of why Sora hit a wall: The Staggering Cost of Compute: A $15 Million Daily Burn People wonder why ChatGPT is so expensive to run compared to other platforms, but AI video generation is on an entirely different spectrum of cost. The "compute" required to generate high-fidelity video is an absolute resource sinkhole. * The Per-Video Cost: Analysts at financial firm Cantor Fitzgerald estimated that generating a single 10-second Sora clip costs OpenAI approximately $1.30 in pure computing power (requiring roughly 40 minutes of total GPU time). * The Annual Deficit: Extrapolating this to millions of users, Forbes estimated that operating the Sora infrastructure was burning through roughly $15 million every single day. That translates to an annualized cost of over $5.4 billion for one single product. * The Subscription Flaw: Even hidden behind a $200/month "Pro" paywall, the math fails. If a power user generates just 20 videos a day, they cost the company over $700 a month in server compute. There is currently no consumer subscription model that makes this "worthy" without OpenAI actively losing money on every generation. The "30 to 10" Sacrifice: A Move for the Fans that Backfired The decision to heavily restrict daily generation limits and reduce video duration down to 10 seconds wasn't a creative glitch—it was a tactical sacrifice made for the community. Faced with "completely unsustainable" economics, OpenAI tried to stretch their server capacity so the general fan base could still experience the platform. However, the strategy was immediately exploited. The moment access was granted, the number of "alt" accounts (secondary accounts used to bypass limits) exploded. Users essentially siphoned the compute power faster than the servers could process it. OpenAI’s financial team had to step in: the choice was either to shut it down or watch the company bleed billions. The Macro Financial Crisis of AI To understand Sora's fate, you have to look at OpenAI's broader financial picture. Despite generating massive revenue, the company is operating at a historic deficit. * In 2024, reports indicated OpenAI lost roughly $5 billion. * By the first half of 2025, despite revenues soaring past $4.3 billion, their net loss widened to a jaw-dropping $13.5 billion, largely driven by the colossal cost of training and running these advanced models. Sora, as incredible as it is, was the most expensive drain on an already bleeding balance sheet. The Legal and Ethical Minefield Beyond the catastrophic server costs, there is the immediate threat of litigation. The rumors involving deepfakes and the unauthorized usage of notorious or deceased individuals’ likenesses have created a liability nightmare. OpenAI’s legal and financial experts know the score: "Take this down now, or we face copyright and defamation lawsuits with zero chance of winning." In a world of strict intellectual property laws, a platform heavily used for "meme culture" is a legal ticking time bomb. The Industry Proof: Look at Google Veo If you doubt the economic severity of this issue, look at the rest of the market. Google possesses one of the largest and most advanced server infrastructures on the planet. Yet, even Google heavily restricts its state-of-the-art video model, Gemini Veo 3. If you pay for the Google AI Pro tier, you are limited to a mere 3 generations per 24 hours in the Gemini app. These are short clips with virtually no advanced editing features. Why? Because even a multi-trillion-dollar giant like Google cannot absorb the energy and compute costs of unlimited AI video generation. Conclusion: A Masterpiece Ahead of Its Economy OpenAI likely intended for Sora to be a high-end, professional tool for enterprise advertising and marketing companies. Instead, the promotional rollout turned it into a consumer meme platform. When you combine $1.30 per-video generation costs, billions in annual burn rates, and the constant threat of lawsuits, the corporate mandate becomes obvious. The technology is God-tier, but our current hardware and economic models simply cannot support it. Welcome to the real world. submitted by /u/Either-Ad-5185 [link] [comments]

We're building features faster than ever. Not sure that's a good thing.

Before you come at me. I like claude code. My engineers like claude code. It's genuinely impressive for what it does. but here's what's actually happening on my team since we went all-in on it: Engineers are now shipping features in hours that used to take days. sounds great right? except nobody's spending more time on the UX just because the code takes less time. They're spending less. the AI generates functional code fast, but it has zero understanding of our product. It doesn't know our users. It doesn't know our design patterns. it doesn't know that we spent 3 months learning that our users hate modal-based flows. So now instead of slow, considered features we get fast, generic ones and the design review bottleneck hasn't improved. It's gotten worse. because now there's 3x the volume of stuff to review and half of it looks like it was designed by someone who's never seen our product before. The fundamental problem is that these tools understand code but not product context. they can build a settings page in 20 minutes but it'll look and feel like every other SaaS settings page on the planet. No awareness of your information architecture, your component library, your specific user mental models. nothing. and I get it, that's not what claude code is for. It's a coding tool. but the downstream effect on product quality is something nobody's talking about. We've basically given the team a faster engine with no steering wheel. What I've started doing is forcing a "context step" before any AI-assisted feature work. basically a doc that captures the product context, relevant design precedents, and user behavior patterns for that surface area. it helps but it's manual and it doesn't scale. Been exploring some tools that try to ingest your actual product context (design system, existing flows, docs) and generate UX from that instead of from a blank slate. early days but the direction feels right. Curious if other product teams are feeling this or am I just bad at process and blaming the tools. submitted by /u/PlentyMedia34 [link] [comments]

I asked Claude how it would visualize itself as an AI agent. Then I built exactly what it described.

A few days ago, I asked Claude a curious question: "If you could choose a visual representation of yourself as an AI agent, working, evaluating input, 'thinking' (computing), how would you represent yourself and your fellow AI agents collaborating?" Claude answered: "The interaction between celestial bodies in a universe is an excellent way to showcase it. Each agent is a planet — a massive entity that consumes energy, emits output, and exerts gravitational influence on its surroundings. Tasks orbit agents like moons. Data flows between agents as spaceships traversing curved arcs through space. And at the center of it all, a black hole — the singularity where completed work collapses, pulling everything toward it. This metaphor works because it scales naturally. One agent is a lonely planet. Five agents become a solar system. The visual language — size, color, orbital speed, surface type — encodes real information without requiring labels or dashboards." So I built it. Event Horizon is a VS Code extension that renders your Claude Code sessions as a gas giant planet in a living universe. You can watch it grow larger as load increases, sprout moons as subagents spin up, and send ships to other agents when collaborating. There's a black hole at the center of everything. Completed work collapses into it. The extension supports Claude Code with one-click hook installation. OpenCode is also supported. Copilot and Cursor are coming. GitHub: https://github.com/HeytalePazguato/event-horizon I thought this community would appreciate the origin story. Has anyone else gotten surprisingly poetic answers from Claude about its own nature? https://reddit.com/link/1rpkcr1/video/5qjit40gl4og1/player submitted by /u/HeytalePazguato [link] [comments]