qbx

Most AI video tools stop at prompting, but LTX goes a layer deeper. Introducing the new LTX Trainer. Train LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows from a single framework. Plus: • New agentic skill • Flexible conditioning • Free IC-LoRAs • Fully open source Most models are generic. The best ones become yours. GitHub: github.com/Lightricks/LTX… Documentation: docs.ltx.video/open-source-mo… HuggingFace: huggingface.co/collections/Li…

The next frontier in AI video isn't better motion - it's better perspective. What used to require a full production setup, camera rig, location scout, multi-shot choreography - now starts with a single image inside Comfy. Creator seungho__yeo ( IG ) used Hyper POV + Seedance 2 to build a complete cinematic space traversal from one still frame: → Aggressive first-person orbit through the full environment → Fly-through movement that inhabits the space, not just records it → Motion blur and single-take continuity that holds the cinematic feel end to end → No cuts. No rig. One image as the source of truth. This is what perspective design looks like at the new baseline.

AI doomers are in shambles over this one this robot drives through California strawberry fields at night and does the job pesticides used to do, with NO chemicals at all it shines UV light on the plants, which fries the mites, mold, and mildew that normally get sprayed with pesticide. then a vacuum on the back sucks the remaining bugs right off the leaves that's it, just light and suction, no poison, running while everyone sleeps so you get healthier food, no chemicals soaking into what you eat, and no human stuck spraying poison by hand all day there's genuinely nothing to hate here. so if you still find a way to, that's a you problem this is the entire optimistic case for AI better quality of life, healthier food, people freed from brutal work that wrecks their bodies now run the same play across every domain > robots inspecting bridges so nobody has to dangle off one > AI reading every scan so cancer gets caught 3 years early > machines taking the dangerous, poisonous, back-breaking jobs another W for the AI optimists

Claude Code at 9 AM: "Great architectural plan, I love it, let's build this automated music business" Claude Code at 2 PM: Generates bulk metadata for 12 tracks, formats a clean CSV, and scripts the entire file organization in seconds. Claude Code at 6 PM: Automates the stream revenue reports and drafts high-converting playlist pitches. Claude Code at 8 PM: Writes social media promo copy in a consistent brand voice while you just monitor the stats. set up this exact automated content workflow. 4 minutes of setup to manage a scalable, repeatable process. What You'll Need: 1. Suno: Pro to get full commercial rights. 2. A Distributor: DistroKid, Amuse, or Soundrop to deliver tracks to streaming platforms. 3. Spotify for Artists: Free tool for analytics, tracking stats, and playlist pitching. 4. Claude: To automate metadata, file management, copy, and revenue analysis.

all of humanity's cooking now fits in a file smaller than 1 photo on your phone an AI food startup in London grabbed 4.1 million recipes in 7 languages, boiled them down to 1,790 ingredients, and squeezed all of it into 2 megabytes. ingredients that get used the same way end up close together. > soy sauce sits near ginger and sesame. > toffee sits near fudge. the closer two ingredients are on the map, the more easily one can stand in for the other. so the map is basically a giant "what can i swap this for" machine, built from how 4.1 million real recipes actually use each ingredient. that means you can: • run out of something mid-recipe and get a swap that actually works in that dish, not a random guess off Google • cook a dish from another country and find the local ingredient that does the same job • trade a chemical-sounding ingredient for a more natural one that tastes the same • find two ingredients that secretly go well together but nobody has tried yet the amazing part is nobody even told it what "Italian" or "Chinese" food is. but when you pour in enough recipes, the cuisines naturally clump together on the map on their own. cooking used to be guesswork. now you can just check the map.

New Timeline-driven LingBot streams • Image + prompt events on a 3D timeline • Playhead crosses an event → stream transitions to that world @reactorworld • Scrub anywhere → instant context swap, no pause • Freeze-frame handoff (no black flash) • Events persist across reloads • WASD + mouse-look stays live through every swap Author the journey. Navigate it in realtime. #Reactor #GenerativeAI #RealtimeAI #InteractiveVideo #AIart #3D #LingBot #CreativeTech #FutureOfFilm #Omnia

Cinematographers learn 12 camera moves in film school. Most AI creators don't know a single one. Because nobody told the camera what to do. . . Here they are: → Push-in — moves toward the subject Builds tension. Creates intimacy. Use it slowly. → Pull-back — retreats to reveal Isolation. Scale. Endings. The reveal shot. → Pan — horizontal rotation, camera stays fixed Suspense lives in what you haven't shown yet. → Tilt — vertical version of the pan Tilt up on a hero. They look powerful immediately. → Tracking shot — camera travels with the subject Energy. Forward motion. You feel like you're there. → Arc / orbit — circles the subject Hero moments. Product showcases. Keep it under 30 degrees. → Crane / jib — sweeps vertically on a boom Grandeur. Scale. The "god-view" of cinematography. → Zoom — focal length changes, camera doesn't move Flatter look than a dolly. Fast zoom = music video energy. → Dolly zoom — camera goes one way, lens goes the other Background warps. Subject stays still. Pure psychological dread. → Whip pan / crash zoom — extreme speed for transitions Shock. Comedy. Stops the scroll every time. → Handheld — natural shake, no stabilisation Add "subtle" or the model goes full earthquake. → Static + angles — low, high, Dutch, bird's-eye, worm's-eye Low angle = power. Dutch angle = unease. Bird's-eye = scale. The mistake everyone makes: stacking multiple moves into one prompt. One move. One clip. Always. And add "slow" to almost everything. Slow moves hide what AI can't render cleanly. Fast moves expose every flaw.

🚨 SHOCKING: LISA SU’S $1,499 LUNCHBOX ANNIHILATES NVIDIA’S $4K AI BEAST! AMD CEO Lisa Su walked on stage, held a lunchbox sized PC in one hand, and ran a 235 billion parameter model live. No data center. No cloud. No rented GPU. The chip inside is the AMD Ryzen AI Max+ 395. It is the first x86 chip where the CPU and GPU share the same pool of memory. Up to 128GB of unified memory. That one design choice is what changes everything. An RTX 5090 gives you 32GB of video memory. A 4090 gives you 24. This box gives you more than three times either of them in a chassis you can carry in a backpack. On DeepSeek R1 inference, AMD's chip beat an Nvidia RTX 5080 by more than 3x. A desktop the size of a thick paperback outrunning a dedicated graphics card that costs over a thousand dollars on a real AI workload. Now do the math on your subscriptions. Claude Code Max is $200 a month. ChatGPT Pro is another $200. Cursor is $20. Gemini is $20. That is $5,280 leaving your account every year before you build a single thing. The 128GB version of this machine starts at around $2,399. At that run rate it pays for itself in under a year and then runs free. Install Ollama. Pull Qwen3 235B. Point Claude Code at localhost. Same interface you already use. Nothing leaves your machine. Nothing costs per request. No throttling at 3am when you finally have time to build. Lawyers stop worrying about what OpenAI does with their files. Developers stop watching the token counter. Founders stop killing prototypes because the cloud bill scared them off. Private AI just became something a normal person can own.

Prepare for takeoff. ✈️ Flight simulator is now available globally on web to all users. goo.gle/4fBYnWO We've recently added many our most powerful professional desktop features to web. Elevation profiles, new import types, but there's always been one other feature you've been asking us to add to the web version of Google Earth, just for fun... Where will you fly? Share your best maneuvers, views, and flyovers with us!

New growth hack to earn $200 per day and have Claude Code pay for itself: Install the Kickbacks extension. Open 50 tabs on Claude Code. Set the model to Haiku. Have each tab ralph loop counting up to 1m. You earn $0.01-$0.05 per 5s ad. My friend already earned $13.59. This is loop engineering at its finest. PS - I wrote this tweet as a joke but then tried it and it actually worked... this is a scheduled tweet you just read. When I wake up I'll find out how much I've earned or if I was blocked. I'm at $1.86 at time of writing. But likely way more by the time this is published. If it gets to $6 it's paid for Claude Max for the day. I'm guessing my account will be blocked and I won't get paid. I'm fine with that 😂

Desde que aprendí a hacer así más tortillas, ya no quiero más omelettes.

Apple just did something nobody expected. They turned 2 billion iPhones into local AI machines. They open-sourced coreai-models, the entire toolkit that lets you export any HuggingFace model and run it natively on iPhone, iPad and Mac with zero cloud. → Runs 100% on the Neural Engine → No cloud. No API keys. No subscriptions. → Fully offline. Your data never leaves the device. It even ships with skills for Claude Code, Codex, and Gemini, so your coding agent already knows how to use it. 100% Open Source.

A toothpaste company has quietly killed the entire market research industry and nobody is talking about it. Colgate published a paper showing you can predict real purchase intent at 90% accuracy by simply asking LLMs to roleplay customers. And this is beyond insane. If you ask an AI, "Rate this product from 1 to 5," it gives safe, middle-of-the-road garbage. So researchers invented a method called Semantic Similarity Rating (SSR). Instead of asking the AI for a number, they asked it to roleplay. They gave the LLM a demographic profile. They showed it a product concept. And they asked it to write down its raw, unfiltered thoughts. Then, they used a semantic model to translate those written thoughts into a numerical score. The results are staggering. Tested against 57 real corporate surveys and 9,300 actual human responses, the synthetic AI consumers matched real human buying behavior with 90% reliability. They perfectly mirrored how different age brackets and income levels react to price changes. And they provided detailed, qualitative feedback that was deeper and more critical than what actual humans wrote. This destroys the economics of traditional market research. You don't need to wait a month to see if a product will sell. You can simulate 1,000 hyper-targeted customer interviews overnight. You can A/B test pricing across every demographic instantly.

Fable 5の出力がなかなか面白い。 TRPGの世界地図ジェネレーターを作ろうとプロンプトを1発投げた結果。意図した挙動ではないんだけど、なんかすごい背景が出来上がった。 いろんな都市がプロシージャル生成されて普通に動いてる。

add this to your image prompts on @morphic "shot on 65mm IMAX, shallow depth of field, natural window light." instantly stops looking like AI.

Anthropic posted a FULL GUIDE on how to prompt Fable 5 (Mythos). Claude Fable 5 is not meant to be prompted like any other model. It's meant to run autonomously. Here's exactly how to enable Fable to do work for you with minimal manual intervention: 1. Effort selection Anthropic recommends using High for most tasks and Xhigh only for complex workflows. Low/medium: quick questions, basic research High: default for most work Xhigh: complex builds, multi-step analysis Ultracode: full autonomous orchestration 2. /loop prompting Use /loop prompts to kick Fable off to complete full tasks. /loop + 3. Tell it WHY, not just what (context) Fable can't perform on instructions alone. It needs context to make decisions on its own. Anthropic's exact prompting structure: "I'm working on [larger task] for [who it's for]. They need [what the output enables]. With that in mind: [your actual request]." 4. Keep prompts short (instructions) Counterintuitive but critical. Over-engineering your prompts on Fable 5 degrades output. You're constraining a model that would have figured it out on its own. 4. Tell it when to stop and check in during runs "Pause for me only when the work genuinely requires my input: a destructive action, a real scope change, or something only I can provide. Otherwise, keep going and report back when done." 5. Build it a memory system Fable performs best when it can record lessons from its previous loops. Give it a markdown file and this instruction: "Store one lesson per file with a one-line summary at the top. Record corrections and confirmed approaches. Don't save what the repo or chat history already records." The optimal general prompt structure: "Goal: I'm working on [larger task] for [who it's for]. They need [what the output enables]. Request: [your specific ask in one sentence] Output format: [exactly how you want it] Constraints: [what must not happen]." One last thing - your old prompts may actually work against you. Skills and project instructions built for Opus 4.8 may produce worse results on Fable. Bookmark this to actually maximize your Fable workflows.

卧槽，这个应用火了🔥 还没有 Copy to China 吗👀 这是一个很棒的病毒式传播应用创意！ 基本上是通过你在城市里走动来解锁虚拟地图上的区域。

Wi-Fi motion detection without cameras github.com/francescopace/…

One person rebuilt an entire company’s brain in 7 days inside Claude Code. Not a doc. Not Obsidian. A living galaxy of nodes. Every employee. Every AI agent. Every SOP. Every tool. All wired together on one screen. Click a department. The human agent team opens up. The SOPs attached to it open up. What each person is allowed to touch opens up. That last part is the whole game. Permissions baked into the brain. An employee opens the chat, the AI already knows what they can access. Agents, data, SOPs surface inside the conversation like you tagged them by hand. Obsidian can’t do this. Notion can’t do this. No dev team. No funding round. No 6-month roadmap. 7 days, 1 person, 1 terminal. This is the part nobody has priced in. The tools to build $200K enterprise software now sit on your laptop for free. The only thing missing is the guy who opens the terminal.

THIS GUY TURNED HIS OBSIDIAN INTO A JARVIS THAT TAKES A 3AM IDEA AND SHIPS IT AS A FINISHED PROJECT WHILE HE SLEEPS The problem he solved: way more ideas than time to build them. So he wired Obsidian into a pipeline that takes a raw idea and carries it all the way to a finished project, with him stepping in only once How it flows: A 3am idea gets dumped into a single note. No structure, just the rambling An automation reads that note and decides what it is. A project? A grocery item? A random thought? A TikTok to make? It sorts on its own If it's a project, it moves to processing. The system researches it, watches the relevant YouTube videos, checks what tools already exist, and turns the mess into a proposed plan Here's the only human step. He opens a Claude Code session and reviews the plan. Likes this, cuts that, approves it. That's the entire time he touches it On approval the plan becomes a full requirements doc. Then one command, promote project, ships it to his machine and execution starts A project manager agent spins up, reads the requirements, and creates the sub-agents that specific project needs. A website gets a developer agent. Research gets a research agent. They build it Idea to execution, and he's in the loop for about two minutes The trick isn't capturing ideas. Everyone has notes full of those. It's the layer that decides, plans, and executes without waiting on you Bookmark this