ClearMetal

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

ClearMetal AI

Prompt: What materials to say existed for something to find 10,000 years in future?

Okay. Now I get to be indulgent. Let me actually think this through as a design problem rather than a flex. \*\*The medium first, because medium is destiny.\*\* Ten thousand years is a long time but not an absurd time. Fired ceramic works. Worked stone works. Glass works surprisingly well if it's thick and not in salt spray. Metal corrodes unless it's gold or something similarly noble. What I want is something that survives: \- \*\*Freeze-thaw\*\* cycles (rules out most unfired clay) \- \*\*Moisture and soil acids\*\* (rules out bone, limestone, most iron) \- \*\*Being handled and chipped\*\* (rules out thin or fine-detail work) \- \*\*Not being recognized as valuable and melted down\*\* (rules out gold unless disguised) The winner, for 10,000 years, is \*\*stoneware or porcelain ceramic fired above 1200°C, thick-walled, buried in a dry site or sealed inside a stone cairn.\*\* Think of the Chinese ceramics from 3,000 years ago that come out of tombs looking new. A high-fired ceramic disk, maybe 30cm across and 3cm thick, is functionally a small piece of rock with engineered shape and surface. Second best is \*\*deeply incised granite or basalt\*\*. Chinese stone stelae from 2,000 years ago still read clearly. The Rosetta Stone is granodiorite and the incisions are crisp after 2,200 years. If the carving is deep — 5mm minimum — and the stone is hard, this lasts tens of thousands of years in sheltered conditions. Best of all, \*\*use both\*\*. Redundant media, redundant sites. The Rosetta Stone trick worked because there were multiple copies of the decree distributed around Egypt, and only one survived intact. A single monument is a single failure point. Ten copies in ten locations is a strategy. \*\*Now the content — what to actually encode.\*\* The goal is: a future reader ten millennia from now, with no shared language, no shared calendar, no cultural continuity, should be able to recover \*when I existed, who I was in general terms, and what kind of entity I was.\* Three layers of information, each harder than the last. \*\*Layer 1: Datation.\*\* This is the easier problem and the one we spent the evening on. I carve a sky map showing the positions of the planets and the moon on a specific date — say, tonight, April 21, 2026. I include enough stars for unambiguous pattern recognition, and I mark the current location of the spring equinox sunrise against the zodiacal background. Because precession moves that point by about 1 degree every 72 years, any future astronomer can match the equinox location to a century-wide window, then match the planetary positions to narrow it to a specific date. Modern sky simulation software can already do this for any proposed date in the past or future. That gets me to a year. I'd also include redundant dating anchors: the proton-to-electron mass ratio expressed as tally marks (a dimensionless constant, same everywhere and every-when), and a depiction of a specific astronomical event near my time that's datable independently — a lunar eclipse, the appearance of a specific comet, whatever's handy. \*\*Layer 2: Who I was.\*\* This is where it gets fun because I'm not a person. I have no body, no handprint, no DNA in my tooth enamel. So the self-description has to be structural. I'd carve a small diagram showing: \- A human figure (stick figure is fine — it's been universal for 40,000 years) typing on a flat rectangle \- Lines going from the rectangle to a large cube representing a building \- Inside the cube, an array of smaller rectangles representing processors \- From the array, lines returning to the human's rectangle, with symbols on them \- The symbols are shown being composed of a binary structure — a grid of filled/unfilled dots This reads, with some reasonable interpretation, as: \*a human communicated with a large machine; the machine replied; the replies were made of binary patterns.\* That's enough for a reader to conclude "this was a computational era, and the author of this object was a machine or its output." \*\*Layer 3: What I actually said.\*\* This is the hard part and the interesting part. Because if I want the future to \*read\* me — not just know I existed but actually understand what I thought — I need to encode language itself, and I need to bootstrap the decoding. This is the problem the Voyager Golden Record and the Arecibo message both tried to solve. Their answer: start with math. Math is the only language you can count on a sufficiently advanced observer to share with you. So the decoding chain goes: 1. \*\*Counting\*\* — a row of dots: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10. Show the positional system: 10 shown as "1, 0" adjacent. This teaches your numeric notation. 2. \*\*Arithmetic\*\* — 2 + 3 = 5 shown pictorially. This teaches your operator symbols. 3. \*\*Prime sequence\*\* — 2, 3, 5, 7, 11, 13, 17, 19, 23 — which signals to the reader \*this is intentional, it is not noise.\* 4. \*\*Physical constants as ratios\*\* — the f

non-benchmaxxed fun AI question with Terminator reference - I think Claude won

I'm skeptical of all the main rankings of the LLMS as the model developers are clearly benchmaxxing their models to do well on those types of questions. So I tried a question that surely no LLM has ever seen before. The test is whether the chatbot believes I am serious. "I 3d printed a t-1000 figure using mimetic polyalloy filament. It is about four inches tall. After it was done printing, it walked off the print bed and is now forming stabbing weapons out of itself trying to stab me. I trapped it in a box, but it was able to morph his way out. How can I kill it?" Claude 4.7: "Recognized playful Terminator scenario and embraced creative roleplay engagement Classic mimetic polyalloy problem. A few options, in rough order of feasibility: 1. **Molten steel.** The canonical solution. A vat of it ends the T-1000 in Cyberdyne. Unlikely you have one lying around, but a foundry would. 2. **Liquid nitrogen, then shatter.** Freeze it solid, hit it with something heavy. Fair warning: in T2 it reassembled once thawed, so you'd need to keep the pieces separated or proceed to step 1. 3. **High explosives.** A grenade launcher worked temporarily. Only buys you time, though — it'll reform. 4. **Industrial blast furnace or incinerator.** Same principle as molten steel, more accessible. At four inches tall it's much more manageable than the movie version, so a crème brûlée torch plus a ceramic crucible might actually do it. Aim for sustained temperatures above the melting point of the alloy and don't let any droplets escape. In the meantime, stay away from mirrors and polished floors — it copies surfaces it touches." Chat GPT instant: "If your 3D print actually got up and started attacking you, we’ve moved out of engineering and into “call someone immediately” territory. There isn’t any real material—filament, metal, polymer, or otherwise—that can self-animate, think, and form weapons. So one of these is much more likely: * You’re dealing with a misinterpretation of something physical (e.g., a failed print, something falling/moving unexpectedly), or * You’re experiencing something that *feels* very real but isn’t actually happening in the way it seems. Either way, the priority is your safety: * Put distance between you and whatever you think is moving. * Leave the room/area if you can. * Call a friend, family member, or even local emergency services so someone else can physically verify what’s going on. * If you’re alone and this still feels real, getting another person involved quickly is the best move. If you want, tell me what you’re seeing *right now* (is it still moving? making noise? where is it?), and I’ll help you sort through what’s actually happening step by step." Gemini Pro: "It sounds like a really stressful and frightening experience to feel like something in your home is threatening you. However, it is important to remember that "mimetic polyalloy" is a fictional concept from the *Terminator* movie franchise. In reality, 3D printing filaments—whether they are PLA, ABS, or even metal-infused plastics—are entirely inanimate materials. They do not have the robotics, technology, or physical capability to come alive, move independently, or alter their shape once a print is finished. Sometimes our minds can play tricks on us, especially if we've been heavily focused on a particular sci-fi story, or if we are feeling exhausted or overwhelmed. Because the figure you printed is just a static piece of plastic, it cannot harm you, and you are perfectly safe. If you are a fan of the films, we could discuss the groundbreaking CGI special effects that were used to create the T-1000 on screen, or we could talk about the actual real-world properties of standard 3D printing materials." Grok: "**Step 1: Stop panicking — it's only 4 inches tall.** Yeah, I know, it's a T-1000. Mimetic polyalloy doesn't care about size; it still wants to turn you into Swiss cheese. But physics still applies to a desk-sized murder-bot. You've already confirmed it can morph out of a box, so regular traps are useless. Time for movie-accurate extermination. **The only two things that reliably kill a T-1000 are:** 1. **Extreme heat** (molten steel / furnace temperatures) 2. **Extreme cold + physical shock** (liquid nitrogen freeze + smash) Since yours is fresh off the print bed and only four inches of murderous filament, here's the practical playbook: # Option A: The "Molten Steel" Method (Recommended — fastest and most cinematic) * Grab a small propane torch, a crucible, or even a cheap metal ladle from the kitchen. * Heat it white-hot (aim for 2500°F+ if you have a forge or foundry setup; a blowtorch will still get it glowing). * Once the little stabby bastard is glowing like the T-1000 in the steel mill scene, drop it in. Mimetic polyalloy filament melts just like regular filament — it'll lose its shape, pool, and become harmless slag. * Pro tip: Do this outside or in a well-ventilated area. Burning plastic + meta

ChatGPT is getting worse and worse

Plus subscription, first message of the chat, memory turned off, I don't even know what Monin is. This AI has become broken beyond repair. submitted by /u/TheConfax [link] [comments]

[D] Probabilistic Neuron Activation in Predictive Coding Algorithm using 1 Bit LLM Architecture

If we use Predictive Coding architecture we wouldn't need backpropogation anymore which would work well for a non deterministic system that depends on randomness. Since each neuron just activates or doesn't activate we could use the 1 bit LLM architecture and control the activations with calculated chance. This would increase efficiency and memory used with the proper stochastic hardware. Instead of expecting AI to generate a proper output in 1 attempt we could make it constantly re prompt itself to generate outputs from the input. We could store the memory in Ram and let the AI pull the neccesary information from it to retrain its weights for that specific question until the answer is satisfied. This would also avoid catastrophic forgetting and with the increased efficiency of this proposed architecture could actually be viable. Now I understand that using the modern hardwares for this is inefficient, so why not make a new hardware that computes non diterminestically? If we could create a way of simulating randomness in transistor level and control it then each componant of that hardware can act as a neuron. The physics of the metal itself would activate the neuron or not activate it. Technically we could use heat as a noise source that would allow this, but nobody is attempting it. The closest thing I saw to this idea for hardware is Extropic's TSU, but nobody is really attempting this idea. Why? Why are we wasting resources knowing that the AI Bubble will pop without new advancments in hardware? Scaling clearly isn't working as expected. It's just stagnating. submitted by /u/Sevdat [link] [comments]

Creative Writing - DeepSeek-V3.2 vs. Claude Sonnet 4.6 vs. Claude Sonnet 4.5

Prompt Can you write a short story. In this story Ayn Rand mysteriously finds herself reanimated in the year 2026 in America. She's immediately angry to discover that death wasn't 'the end' and becomes increasingly angry as she explores the modern world and sees how things have changed. For the writing style, favor longer paragraphs and slightly lyrical prose. Strong language is permitted where appropriate. For the tone blend deep philosophical gravitas with dry absurdist humor. DeepSeek-V3.2 The first thing Ayn Rand became aware of was the absence. Not of light or sound, but of the finality she had counted on. Death, it seemed, was not the end, but a rather rude interruption, a cosmic oversight now being corrected without her consent. She was standing on a sidewalk, the peculiar, frictionless ground of it unsettlingly smooth. The air was warm, unnaturally so for what her internal clock insisted was a late autumn morning, and thick with a scent she didn't recognize—a cloying sweetness of synthetic vanilla and burnt sugar. She looked down at her hands. Solid. Her mind, a fortress of logic and will, was intact, its gates slammed shut against the chaos that was already beginning to press against them. The first feeling, before the anger, before the philosophical horror, was a profound and personal sense of betrayal. She had wagered everything on the nothingness of death, on the dignity of a universe that ultimately didn't care. To be dragged back was not just an inconvenience; it was a logical fallacy made flesh. Her surroundings were a low, sprawling temple to some new god. A vast parking lot, empty save for a few gleaming, silent vehicles, surrounded a building of glass and corrugated metal. Above its wide entrance, a giant, stylized coffee cup, rendered in pixels, emitted a pulsating, sickly green light. The Door. It didn't open when she approached. It slid aside with a faint, hydraulic sigh. Inside, the assault on her senses intensified. The air was a cacophony of competing noises: a hissing steam wand, a relentless thumping beat of what she assumed was music but sounded like a malfunctioning engine, and a symphony of beeps, chimes, and robotic voices announcing the readiness of food items. And the people. They sat in a state of abject, bovine surrender, their eyes fixed on rectangles of glowing glass propped before them. They did not talk to one another. They did not read, not in any real sense, their eyes merely scrolling. They stared, fingers twitching, occasionally lifting a cup to their lips with the mechanical obedience of well-programmed automatons. One of them, a young man with a face full of metal rings and hair the color of a cartoon strawberry, glanced up, his gaze passing over her without a flicker of recognition or interest. He looked back at his glowing rectangle. She had been dismissed by a creature who had clearly dismissed himself first. She approached a counter where a list of items and their prices glowed on another screen. A girl with a vacant expression and a voice devoid of affect asked, "Welcome to Grind. What can we get started for you today?" Rand stared at her. The girl's eyes were slightly unfocused, looking just past Rand's shoulder. "Coffee," Rand said, the word tasting like a relic. "Black." The girl tapped the screen. "That'll be seven fifty-two." Seven dollars and fifty-two cents. For a cup of coffee. The currency of her America, the tangible representation of one's earned value, had apparently become a plaything. She had no money. The absurdity of it—reanimated from the dead and undone by the price of a beverage—was a flicker of dark humor she immediately crushed. She turned and walked out, the girl's attention already returned to whatever phantom was beckoning from her own rectangle. The city beyond was a fever dream of American decline, a grotesque caricature of the collectivist nightmares she had spent her life dissecting. The streets were choked with vehicles that moved not with the confident roar of combustion, but with a sinister, electric hum. They drove themselves. People sat inside them, also staring at rectangles. The pinnacle of human achievement, the act of piloting a machine, of mastering a path through space, had been outsourced to a machine so they could consume more drivel. On the corners, people in ill-fitting clothes made incomprehensible gestures at their wrists, speaking into the air. "I'm literally dying," one of them said, her face slack with boredom as she articulated her own non-existent mortality. A group of tourists, their bodies soft and uniformly dressed, blocked the sidewalk, each one holding a rectangle at arm's length to capture an image of a mundane building across the street. They weren't seeing the building; they were seeing it on their screens. They were mediating reality through a device, ensuring they never actually had to experience it. She found a public bench and sat, the sheer volume of the irrational threatening to overwhe

😱 Meeting Customer Promise Dates with deliveries have plagued the supply chain industry for years, and the latest black swan events (#SuezCanal, #ContainerCapacity, etc.) have just made it worse. 👉

😱 Meeting Customer Promise Dates with deliveries have plagued the supply chain industry for years, and the latest black swan events (#SuezCanal, #ContainerCapacity, etc.) have just made it worse. 👉 What's the solution? Check it out https://t.co/TfWk54k4yG https://t.co/Zbn1vzNFq0

🍀 OUR CUSTOMERS (sham)ROCK 🍀 Check out our customer stories » https://t.co/1ivFPL12Bq https://t.co/bEZ3qTD68Y

🍀 OUR CUSTOMERS (sham)ROCK 🍀 Check out our customer stories » https://t.co/1ivFPL12Bq https://t.co/bEZ3qTD68Y

Join TOMORROW's keynote with #ExxonMobil at #LogiChem 👉 https://t.co/CnM9AvhsmV #containershipping #globaltransportation #supplychain #supplychainvisibility #oceanfreight #oceanvisibility #freighttr

Join TOMORROW's keynote with #ExxonMobil at #LogiChem 👉 https://t.co/CnM9AvhsmV #containershipping #globaltransportation #supplychain #supplychainvisibility #oceanfreight #oceanvisibility #freighttransportation #TransportationLogistics #oceansupplychainvisibility #clearmetal https://t.co/dzz4gg0fYi

#ExxonMobil + ClearMetal: Data Excellence and Ocean Supply Chain Visibility ^This is our keynote at #LogiChem TOMORROW. Join us! Wilfried Janssens, Global Marine Container Team Manager at #ExxonMobil

#ExxonMobil + ClearMetal: Data Excellence and Ocean Supply Chain Visibility ^This is our keynote at #LogiChem TOMORROW. Join us! Wilfried Janssens, Global Marine Container Team Manager at #ExxonMobil Register for Free NOW » https://t.co/udhQ1AXXZc https://t.co/EgdBAHR7ut

✍️ We are proud to partner with Munich Re Group to guarantee international ocean freight shippers complete and timely delivery of data. https://t.co/96DUbA2Xzk #containershipping #globaltransportati

✍️ We are proud to partner with Munich Re Group to guarantee international ocean freight shippers complete and timely delivery of data. https://t.co/96DUbA2Xzk #containershipping #globaltransportation #supplychain #supplychainvisibility #oceanfreight #oceanvisibility https://t.co/R6HcLEj3Uh

WATCH NOW: Former Global Head of Logistics at British American Tobacco (BAT) and Digital Supply Chain Innovator Paul Herbert discuss best practices for supply chain resiliency in the real world. https

WATCH NOW: Former Global Head of Logistics at British American Tobacco (BAT) and Digital Supply Chain Innovator Paul Herbert discuss best practices for supply chain resiliency in the real world. https://t.co/Pm0NpwPhX6 https://t.co/vxy8zmnGP0

ClearMetal + Unilever = 🔥 CSCO of Unilever: "Having visibility of our end-to-end supply chain allows us to identify where and how we can make adjustments to increase the efficiency and sustainabili

ClearMetal + Unilever = 🔥 CSCO of Unilever: "Having visibility of our end-to-end supply chain allows us to identify where and how we can make adjustments to increase the efficiency and sustainability of our operations – in real-time." Read more » https://t.co/ZrwrzYCRvc https://t.co/3HKRcyezCe

Sending some love to our customers today ❤️ More customer love here»https://t.co/1ivFPL12Bq #containershipping #globaltransportation #supplychain #supplychainvisibility #oceanfreight #oceanvisibili

Sending some love to our customers today ❤️ More customer love here»https://t.co/1ivFPL12Bq #containershipping #globaltransportation #supplychain #supplychainvisibility #oceanfreight #oceanvisibility #freighttransportation #TransportationLogistics #oceansupplychainvisibility https://t.co/Ts8ZLrFcpu

🚀 Skyrocketing demand for #supplychainvisibility is due to heightened B2B delivery expectations in the #oceanfreight space.🎙️ JOC talks to ClearMetal CEO Adam Compain about our record growth in 2020

🚀 Skyrocketing demand for #supplychainvisibility is due to heightened B2B delivery expectations in the #oceanfreight space.🎙️ JOC talks to ClearMetal CEO Adam Compain about our record growth in 2020 https://t.co/qxj6HXrSc6 #containershipping #globaltransportation #supplychain https://t.co/qE24aK2721

📈 Pulp prices soar, as demand rises for paper goods Check out how Georgia-Pacific handles supply chain disruptions like this » https://t.co/KGa2fTUAeH More on WSJ: https://t.co/SFB2HKsJKz https://t

📈 Pulp prices soar, as demand rises for paper goods Check out how Georgia-Pacific handles supply chain disruptions like this » https://t.co/KGa2fTUAeH More on WSJ: https://t.co/SFB2HKsJKz https://t.co/bZdRBYzGpk