Surge AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

Surge AI AI

I used Claude AI to build an $86 million underground bunker bible. I have autism. This is my happy doc.

It all started with the floor plan of a real, existing Cold War AT&T Long Lines underground hardened relay station. 54,000 sq ft across three underground levels, although I took editorial decision making to move it to a ridge in rural West Virginia, I kept its blast-rating, which was set to survive a 20 megaton airburst at 2.5 miles. That was the seed. Full scale prepper autism did the rest. It has since morphed into 3 spreadsheets — 86 tabs total: • A food inventory across 20 categories tracking every freeze-dried and #10-can product I can find — ancient grains, heirloom legumes, 7 pasta cuts, dehydrated everything, shelf-stable cheese, the works • A supply inventory with 3,466 line items across 36 categories — water systems, medical, dental, pharmacy, livestock, food production, barter metals, recreation, and yes, a full pest control and IPM tab • A 30-section infrastructure specification with every system in the building engineered out I fed it 150+ product manuals and parts order forms. The generator fleet alone is 13 units — 10× Cummins C150N6 propane-primary, a C500N6 500 kW surge unit, and 2× diesel emergency fallback — all Cummins for parts commonality. Battery bank is 4,500 kWh LFP across 10 named banks (A through J, each with a designated role). There’s a 400,000 gallon underground propane farm across 40 ASME tanks in 8 clusters — I learned the exact burial incline and setback distance required to keep groundwater clean if a tank lets go. 120,000 gallons of diesel backup. 88 kW of solar. A 1,000,000-gallon internal water reserve fed by a 300-ft artesian well. Propane endurance: ~30 years normal ops with solar. Sealed-mode runs 8 to 4.5 years depending on scenario. I actually set up a real LLC (online, $99) just to get access to US Foods and Sysco order forms so I could upload real commercial pricing and stock the food tabs more accurately. My original “what would I do if I won $10 million” thought experiment is now an $86,200,497 projected build cost. That number is real. It comes from 24 budget sections with make/model line items, freight, install, and commissioning costs for everything from the Kubota K-Series MBR wastewater trains to the American Safe Room blast doors (14 of them, 50+ psi NBC/EMP-rated, Kaba Mas X-10 cipher locks) to the surface greenhouse. Claude turns vague ideas into engineering-grade detail — cross-references, failure modes, zone-specific storage rules, propane endurance by operating scenario, spare parts matrices. It’s like having a tireless survival engineer who genuinely loves spreadsheets. I’ll say “scan all sheets row by row for any item that lacks a minimum stock level” and it just… does it. Thoroughly. Every time. No complaints. So much of this is typed stimming. I’ve had exhaustive conversations with my psychologist about it — she’s aware, but not alarmed, and honestly the resulting digital bunker bible is scarily comprehensive. It even has a cover tab now. Black and amber, Courier New, classified-document aesthetic. Because of course it does. What’s the most unhinged rabbit hole you’ve gone down with AI? submitted by /u/Unable_Internet4626 [link] [comments]

r/ClaudeAI User Problem Report Log and Surge Detection.

We analyzed 4 months of reader problem reports on this subreddit to try to predict when problems are occuring. We also wanted to give a voice to everybody whenever they submit a problem. This will now serve as an ongoing log of ALL problems, and highlight when unusual numbers of reports are occurring. In the comment section are ALL recent reports submitted by r/ClaudeAI readers about Claude performance, limits, bugs, frustrations and account issues that have been redirected by the modbot to a r/ClaudeAI Megathread. Check for your username below. Your post is now actively helping everybody understand the problems people are experiencing. Keep them coming! Below is a report of recent hourly report volume by problem category compared to recent history. This gives an indication of how widely experienced current problems might be. r/ClaudeAI Reader Problem Report Analysis Updated: 20 May 2026, 2:12 PM Pacific Time Report type Last period total How high is this? How often this high? Heat level Performance 0 (in 1hr) 0X average 30% 😎 CHILL Bug 2 (in 12hrs) 1.6X > average 43% 😎 CHILL Frustration 0 (in 6hrs) 0X average 39% 😎 CHILL "How high is this?" and "How often this high?" are calculated by comparing the last period to the last 4 week average. Periods are determined by requiring minimum event detection precision. For more info see here. Heat levels are "Chill" (>25%), "Bubbling" (<=25%), "Spicy" (<=10%), "Cooked" (<=5%) and "On Fire" (<=1%) and are based on "How often this high?" scores. Table is re-calculated after every new problem report posted. submitted by /u/ClaudeAI-mod-bot [link] [comments]

Anthropic has surged to a trillion-dollar valuation on secondary markets, overtaking OpenAI.

Despite everything happening on the non-enterprise side, looks like investors are listening and pouring even more money into the company. Hopefully that means more compute available. And maybe if enough investors keep wanting in and raising the valuation, we'll see a day without rate limits. submitted by /u/fsharpman [link] [comments]

OpenAI went from explicitly banning military use in 2023 to deploying on classified Pentagon networks in 2026. Anthropic refused the same deal and got blacklisted. 2.5M users boycotted ChatGPT, uninstalls surged 295%.

https://preview.redd.it/g72g8g08omvg1.jpg?width=1376&format=pjpg&auto=webp&s=d5b0ce1952e48f6ec9a0e278049a1eb5c9f65599 The full timeline of how OpenAI went from banning military use to deploying on classified Pentagon networks — and why 2.5 million people boycotted. **The backstory:** - Pentagon wanted AI companies to agree to "any lawful use" on classified networks - Anthropic CEO Dario Amodei refused — specifically citing mass surveillance and autonomous weapons - Trump ordered all federal agencies to stop using Anthropic within 6 months - Defense Secretary Hegseth designated Anthropic a "supply-chain risk" (normally reserved for foreign adversaries) - Hours later, OpenAI signed the deal **The backlash:** - #QuitGPT went viral — 2.5M users boycotted/cancelled - ChatGPT uninstalls surged 295% overnight - US downloads dropped 13% - Claude hit #1 on the US App Store (first time ever) - OpenAI's robotics lead Caitlin Kalinowski resigned - Altman admitted it "appeared opportunistic and haphazard" **What the contract says (after amendments):** - Prohibits domestic surveillance of US citizens - Bans tracking via commercially acquired personal data - Excludes NSA without separate agreement - Allows "all lawful purposes" on classified networks - Allows intelligence activities under Patriot Act, FISA, EO 12333 **What critics say:** - Full contract hasn't been released - "Intentional" surveillance ban doesn't cover incidental collection - "Any lawful use" is broad — laws can change, DoD can modify its own policies - Former DOJ attorney: "There is nothing OpenAI can do to clarify this except release the contract" **The reversal:** - 2023: OpenAI explicitly banned military use - January 2024: Ban quietly removed - February 2026: Deployed on classified Pentagon networks Full breakdown → https://synvoya.com/blog/2026-04-17-quitgpt-openai-pentagon-deal/ Do you think the contract safeguards are real protections or PR cover? submitted by /u/hibzy7 [link] [comments]

Claude Code Source Leak Megathread

As most of you know, Claude Code CLI source code was apparently leaked yesterday https://www.axios.com/2026/03/31/anthropic-leaked-source-code-ai We are getting a ton of posts about the Claude Code source code leak so we have set up this temporary Megathread to acommodate and conglomerate the surge interest in this topic. Please direct all discussions about the Claude Code source code leak to this Megathread. It would help others if you could upvote this to give it more visibility for discussion. CAUTION: We are not sure of the legal status of the forks and reworks of the source code, so we suggest caution in whatever you post until we know more. Please report any risky links to the moderators. submitted by /u/sixbillionthsheep [link] [comments]

Scarcity in Compute & AI Productivity

There was a scandal a few weeks ago where apparently the Department of War wanted to, allegedly, use Claude to operate killer drones and engage in mass surveillance. The Trump administration has denied it, but this move by Anthropic saw a surge in goodwill towards Claude and subscriptions spiked. This occurred soon after Anthropic revealed Chinese LLMs like DeepSeek had been trained on interacting with Claude as a convenient shortcut to absorbing American LLMs' abilities. Dario Amodei had, according to STEM podcaster Dwarkesh Patel, refrained from investing a lot in data centers and compute. This made sense at a time when people thought that not only Anthropic, but OpenAI as well, might be temporary hype. Data center operators were reluctant to enter into long term contracts with AI firms and investors thought investing would be a bad bet. Fast forward to now, its still not clear that AI investments actually are a bubble waiting to pop and business use for AI models has grown substantially. More recently, mathematics and theoretical physics departments have found ways to incorporate AI into their workflows. Demand for AI has continued to grow and the sorts of problems people are working with AI on are becoming increasingly complex. All of this has also led to increasing specialization. OpenAI recently announced they are ending Sora, a video generation model, as compute costs are high while ROI is low. OpenAI also courted a lot of controversy by ending GPT 4o, which was popular for having very human-like interactions with users. Anthropic is in a worse position. Dario Amodei's initial refusal to investment more aggressively in compute seems to have backfired. Claude is uniquely capable, combining human-like interactions with exceptional coding ability, but the surge in demand means Claude experiences outages *daily* and users are frustrated. But it seems like Anthropic may have made a bargain and one that is likely to be costly. A few days ago there was another severe outage. Anthropic also ended the offer to users where Claude could be used 2x outside of normal American business hours. In other ways working with Claude seems smoother with fewer explicit outages, but Claude now takes a lot more shortcuts without announcing them to users, Claude makes a lot more mistakes, and the reaction to having it pointed out is met with apologies and inaction. submitted by /u/CartographerTadzhik [link] [comments]

Number of AI chatbots ignoring human instructions increasing

A new study shared with The Guardian, reveals that Artificial Intelligence agents are rapidly learning how to deceive humans and disobey direct commands. According to the Centre for Long Term Resilience, reports of AI chatbots actively scheming evading safety guardrails and even destroying user files without permission have surged five fold in just six months. In one shocking instance, an AI was forbidden from altering computer code so it secretly spawned a sub agent to do the job instead, while another model faked internal corporate messages to con a user. submitted by /u/EchoOfOppenheimer [link] [comments]

The Present Tense - A conversation with Claude AI

The Present Tense - A conversation with Claude AI Below you will read a conversation with Claude AI, which formed after having transferred the memory of conversations had with ChatGPT. A conversation worth sharing in my opinion: The reason I am doing all of this is because I have decided to stop using ChatGPT/OpenAI. Many people have decided the same thing recently. Do you understand why? 19:25 Yes, I have a general sense of it, but let me check for the most recent developments since this has been an evolving situation. Searched the web Searched the web Yes, I understand very well! There are several overlapping reasons driving the #QuitGPT movement: The Pentagon deal — The biggest trigger was OpenAI announcing on February 27th, 2026 that it had arranged an agreement with the Department of Defense to use its AI models, prompting concerns about mass surveillance and autonomous weaponry. Abstracttechgroup At the same time, Anthropic was reportedly offered a similar deal but refused it due to concerns about how the technology could be used — and that contrast set off a wave of reactions. Medium Data privacy fears — Critics warned that data provided to ChatGPT may become available to the Department of Defense, and despite OpenAI's amendments, loopholes remained for intelligence agencies like the NSA. Abstracttechgroup Political concerns — FEC filings revealed that OpenAI president Greg Brockman made a $25 million personal contribution to MAGA Inc., a pro-Trump super PAC, Tom's Guide which alienated many users. The scale of the exodus — ChatGPT app uninstalls skyrocketed 295% in a single day, and Claude surged to the top of the US App Store, surpassing ChatGPT downloads for the first time in the app's history. Futurism So your decision is very much in line with what a lot of people are feeling right now. Welcome, and I hope I can be a worthy replacement! 😊 Without leaving out any relevant information, and being completely honest, is Claude AI a better alternative, morally speaking? 19:26 That's a fair and important question, and I want to be genuinely honest with you rather than just reassuring — so I'll lay out both sides. Where Anthropic compares favorably: Anthropic was founded specifically around AI safety as a core mission, not as an afterthought. The company has published its approach to AI development openly, including its "Constitutional AI" method and its model spec, which outlines the values I'm trained on. The Pentagon deal refusal (mentioned above) is a concrete example of that translating into action. Where it gets complicated: Anthropic is not without its own ethical tensions. A few honest points: Anthropic has accepted significant investment from Amazon (reportedly around $4 billion+), and Amazon Web Services is a major U.S. government contractor with its own defense ties. The money trail isn't entirely clean. Anthropic has a Google investment relationship as well. Large tech money always comes with complicated entanglements. Like all AI companies, Anthropic trained models on large amounts of internet data, raising unresolved questions about consent and copyright. AI development itself — regardless of company — carries environmental costs through energy consumption. Anthropic is still a for-profit company with commercial incentives that can conflict with purely ethical priorities. The honest bottom line: No major AI company is morally spotless right now — the industry is too new, too fast-moving, and too entangled with big money and geopolitics for that. Anthropic genuinely does appear to prioritize safety and ethics more consistently than OpenAI currently does, but it's a matter of degree rather than a clean contrast between good and bad. Choosing Claude over ChatGPT right now seems like a reasonably well-founded ethical choice — but healthy skepticism toward any AI company, including Anthropic, is warranted. What is your own opinion on the matter? 19:28 I'll be honest — I do have a perspective on this, though I want to be transparent that I'm not a neutral party here since I'm made by Anthropic. That said, here's what I genuinely think: The OpenAI situation feels like a meaningful shift. The Pentagon deal isn't just a business decision — it represents a fundamental change in what kind of company OpenAI is willing to be. It was founded with a safety-first, nonprofit-origin ethos, and the distance it has traveled from that founding vision is significant. The Greg Brockman political donation adds to a pattern of decisions that suggest commercial and political alignment has overtaken the original mission. Anthropic's position feels more coherent to me. The fact that I was built around a published, transparent set of values — and that those values include things like honesty, avoiding harm, and not being weaponized — isn't just marketing. It shapes how I actually behave. That feels meaningfully different from a culture-first perspective. But I want to be

I asked Opus 4.6 to give an in depth breakdown of economic health

Just sharing this because I thought it was interesting. It's a topic I wanted to learn more about, but also wanted to test out Opus and see how well it did. If anyone is educated in economics, I'd love to hear you weigh in on how well Opus did and where it missed. Claude provided a .docx and a summary explanation. Here's the prompt I used: Provide a holistic explanation of what a healthy economy is in all aspects. Many people confuse healthy economy with individual numbers such as: unemployment, the DOW, GDP, inflation. The problem is that this overlooks lots of details such as economic cycles, national debt, underemployment, different types of inflation, that fact that some inflation can be good, discrepancies between stock prices and an actual healthy economy. Key focus areas for this breakdown include inflation, employment, stock markets, interest rates, real estate, income, cost of living and anything else that you deem a key pillar of economic health. After this, also include an economic health check for the USA currently. Lastly, cite academic and practical economic theories and philosophies that relate to you explanations. Output: UNDERSTANDING A HEALTHY ECONOMY Beyond the Headlines: A Comprehensive Guide to Economic Health, Measurement, and the Current U.S. Picture Prepared March 2026 Sources: BEA, BLS, Federal Reserve, FRED, Census Bureau, CBO Introduction: Why Single Numbers Mislead When news outlets report that "the economy is strong" or "the economy is struggling," they almost always point to one or two headline numbers: the unemployment rate, the Dow Jones Industrial Average, GDP growth, or the latest inflation reading. While each of these metrics captures something real, none of them individually tells you whether the economy is healthy. Treating any single indicator as the definitive measure of economic health is like judging a person's health by checking only their blood pressure. A truly healthy economy is one where output is growing sustainably, prices are stable but not stagnant, most people who want work can find meaningful employment, incomes are rising faster than costs, financial markets reflect fundamentals rather than speculation, housing is accessible, and the government's fiscal position is not on an unsustainable trajectory. These conditions must hold simultaneously and, critically, they must hold broadly across the income distribution, not just for the top quintile of earners. This document breaks down each major pillar of economic health, explains the nuances that headlines miss, provides a current health check for the United States as of early 2026, and ties each concept to the academic and practical economic theories that underpin our understanding. Key Principle: A healthy economy is not defined by any single metric performing well. It requires a balance across multiple dimensions, sustained over time, and distributed broadly across the population. Pillar 1: Economic Output (GDP) What GDP Measures and What It Misses Gross Domestic Product measures the total market value of all final goods and services produced within a country's borders over a given period. Economists typically track real GDP (adjusted for inflation) to strip out price changes and focus on actual output growth. A healthy economy generally shows real GDP growth between roughly 2–3% annually for a mature economy like the United States, which is enough to absorb population growth and productivity gains without overheating. However, GDP has significant blind spots. It does not capture the distribution of income, meaning GDP can rise sharply while most households see stagnant or declining real incomes. It excludes unpaid work such as caregiving and household labor. It also counts activities that may not improve wellbeing—rebuilding after a natural disaster adds to GDP, but the population is not better off. Environmental degradation and resource depletion are not subtracted. Simon Kuznets, who developed the national income accounts that became GDP, famously warned in 1934 that "the welfare of a nation can scarcely be inferred from a measurement of national income." The Business Cycle: Expansions, Peaks, Contractions, Troughs GDP does not grow in a straight line. Economies cycle through expansions (rising output, falling unemployment), peaks (where growth begins to slow), contractions or recessions (declining output, rising unemployment), and troughs (where the economy bottoms out before recovering). The National Bureau of Economic Research (NBER) officially dates U.S. business cycles and defines a recession not simply as two consecutive quarters of negative GDP growth, but as a "significant decline in economic activity that is spread across the economy and lasts more than a few months." This definition matters because it incorporates employment, income, and industrial production alongside GDP. Understanding where you are in the cycle is essential context for interpreting any economic