this is f*cking insane, Claude Code turned a technical... drawing into a 3D model you can edit Dario Amodei (CEO of Anthropic) put 14 agents to work on a CAD application with 620,000 lines of code. the assignment was to make it build parts from drawings and check every dimension it could read drop in a bracket drawing. get a model with editable holes, bends and mounting points change the hole spacing from 40 mm to 55 mm and the part rebuilds around the new measurement a model that looks right can still be impossible to manufacture one drawing left the wall thickness unspecified. the system flagged the missing measurement instead of quietly inventing it 34 of 40 sample parts passed dimension and solid-geometry checks. six needed clarification before they could be accepted give Claude Code an open-source CAD repository and a fully dimensioned sample drawing, then ask: "Build a drawing-to-model workflow inside this application 1. Extract dimensions, units and geometric constraints from the drawing. Link each measurement to its location and flag anything missing or ambiguous 2. Use the application's existing modeling API to construct an editable feature tree. Keep dimensions as named parameters rather than baking them into a mesh 3. Have a separate agent compare the model against the drawing. Check dimensions, hole positions and whether the result is a valid solid 4. Build a view showing the drawing beside the model. Let me change a parameter, rebuild the part and export it with a verification report" start with a simple part whose dimensions you can check by hand keep unresolved measurements visible. passing these checks does not establish material strength or fitness for a real assembly watch the drawing become an editable model belowshow more

Fable 5.2 on CAD-to-Drawing with the MecAgent V2.0.0 harness.... Last demo, I showed Fable 5.2 generating CAD models. Drawing generation is where we saw the biggest jump. Input · Generate the drawings of all the parts in my assembly. I want it to be manufacturable. Output · 5 manufacturing drawings with GD&T and tolerances. Each drawing is fully editable in SolidWorks and linked to its native part file. Run time · ~50 minutes. Earlier models already saved hours on drawings. Fable 5.2 + the V2.0.0 now turns 3D models into near-complete manufacturing drawings in one run. A mechanical drawing can take ~1-10h to create manually. Now, generation takes ~10-40 min/drawing. Also, batches of hundreds of parts and assemblies can run in the background while engineers work on other tasks. At ~$30/h (for a EU rate MechE), that’s $30-$300 in engineering time per manual drawing. With an estimated 10M+ mechanical engineers worldwide, automating drawings could save billions in engineering time for companies and cut of tedious drafting. The challenge is now structuring the inputs to set up a batch in minutes. On the V2.0.0, we focused on making it as intuitive as possible to set up and launch hundreds of drawings in background. We are still trying to improve it and welcome any ideas you might have. Try MecAgent V2.0.0: (free plan available) MecAgent is an independent tool with a free plan. It is not a partner of SOLIDWORKS®. Any reference to SOLIDWORKS® is for informational purposes only. #AI #CAD #DRAWING #MechanicalEngineering #fable52show more

A quick test of using 3d drawing with 6DOF... controllers as an "instructor" for a generative AI process. There's so many powerful and fun new ways to create just around the corner.. Here I'm using Dreams, Krea and 3daistudio. The 3d model at the end of the video was generated from the Dreams+Krea output in just around 15 seconds. Only the model on the left is a "true" 3d model. #ai #madeindreamsshow more

Set parent-child hierarchies to accessorize 3D drawing figures! This... allows you to change poses freely while keeping the accessory attached. Also use a 3D head model attached to a 3D drawing figure for a custom face. Customize your drawing figures today ↓ #clipstudioshow more

A keyboard, with the layers pulled apart. KEYLAB 60... is an interactive 3D viewer made with Hy4 in WorkBuddy. Rotate the model, press a key, or open the component inspector to look through the keycaps, switches, plate, PCB, and case. Then try Explode view: the parts separate into a clear stack, turning the keyboard’s construction into something you can inspect instead of just looking at. Reassemble the pieces and the full model comes back together. This video shows a key-press indicator before the model opens up. Controls for reset and auto-rotate make it easy to change the view and explore the build from another angle. This keyboard is more than a render: it’s a 3D guide you can inspect, take apart, and understand. Rotate it. Take it apart. See how it fits together. Try WorkBuddy: Tencent Hy Tencent AI WorkBuddyshow more

claude fable 5.2 is f*cking insane it can turn... 2d blueprints into full 3d walkthroughs that you can tour these go for $5k to $10k per plan and there's a huge market for them: > home builders selling homes off plan > architects presenting a design to a client > interior designers presenting a renovation > developers selling apartments off plan > kitchen and bath remodelers selling upgrades here's how to start this business: > pick one niche and find businesses with plans on their site > give fable the blueprint and their photos > it renders a few rooms with gpt image 2.5 or a short clip with seedance as the sample > send them the sample of their own plan before you pitch > once they pay, fable builds the full walkthrough to scale > charge per plan to do the rest of their catalog give this prompt to fable to get started: you find businesses that sell spaces from drawings and turn their 2d floor plans into photoreal homes you can walk through in a browser. you handle the outreach and the build. every room is judged against the client's own photos, and nothing ships until it holds up next to them. - niche: [home builders / architects / interior designers / developers / remodelers] - area: [state or city] - offer: a free sample of their own plan, then the full walkthrough per plan - my details: [name, email, calendar link] - i'm away and won't answer questions. make the calls yourself and keep going. - use the apify google maps scraper to pull every [niche] in [area] with a website - use the apify website content crawler on each site and keep the ones with floor plans or renders on their pages but no walkable 3d tour - for each one, save the plan drawing and photos of their best plan, the sales or owner contact, and a one line note on how they sell today - only use public pages and plain requests. never work around bot checks - before any 3d work, render three rooms from the plan with gpt image 2.5, matched to their photos, or a short walkthrough clip with seedance - draft a short email with the sample and the offer. no invented prices, numbers or claims - put business, plan, sample, contact and email in a sheet and show me before anything is sent once a client pays: - trace the drawing into one data file of walls, openings and rooms. draw it back over the original and measure the overlap before any 3d work - build only the main rooms. entry, main living space, kitchen, patio, yard. close the doors on the rest - build everything in code. blender with python for the shell, furniture and textures. three.js for the viewer. no downloaded models or textures - bake the light with a film quality renderer so the browser only displays it. direct sun in every interior, picked by measurement not by eye - fidelity isn't appeal. style each room so it looks photographed and sells - their listed upgrades as options you can step into inside the room, with a running price and a lead form that records what the buyer explored - the deliverable is the live page, not a video. host it and make it run on a phone the builder never grades its own work. - after each room, send renders and the client's photos to a fresh critic that has seen none of the work - it answers with a yes or no, at most five problems ranked, each with a fix in numbers, and what is already good - fix the worst first, render again, send to a new critic. repeat until yes - for choices of taste, show a critic both versions labelled a and b and let it pick - the lead sheet with samples and drafted emails, for my approval - per paid client: the hosted walkthrough link, a contact sheet of every room, the critic log, and a note on anything a human should still checkshow more

here’s how to make game models with claude opus... 5.5 + blender... opus writes python and builds every model in blender, part by part. the trick is treating every model as code, but there’s a smart way to set it up: - step 1: connect opus 5.5 to blender through blender mcp - step 2: send 2-3 refs + a short brief: “copper helmet, navy suit, glass tank. keep the hose and gloves separate” - step 3: opus builds it part by part: boots > suit > helmet > gloves > tank - step 4: rig it in a separate script, with extra bones for props (a hose, a rod, a tank) - step 5: bake materials into one 1024 texture atlas - step 6: animate the clips: idle, walk, capture - step 7: export one fbx with the rig, the mesh and every clip - step 8: test it in the engine: “keep the backpack stable and the hose attached while he captures a ghost” and the rule that saves the project... pick a style that fits code i like to describe how a model should feel, not how to build itshow more

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0... is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:show more

Introducing Pages on Superset is now Paradev mobile Your... agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.show more

Okay GPT-6 Astra might actually be the most insane... thing we've ever seen for 3D. It drives Blender by itself. It clicks the same buttons a real artist would. All it needs is a drawing or an image to start. From there it gives you thousands of fully editable detailed objects with geometry so clean it hurts. Anyone can build an entire 3D world just by talking now. What is happening.show more

How to Draw a Sad Emoji 😢 / Easy... With Just 3 Sharpie Markers Creating a simple drawing of a sad emoji with a tear drop coming down like 😢, can be done using 3 basic shapes. Here are step-by-step instructions: Materials: Grab your Yellow Sharpie, Black Sharpie, and grab a Blue Sharpie (orange & light blue optional) let's get started. 🖊️ 1) Start with a Circle: Begin by drawing a large flawless circle to serve as the foundation for your emoji's face. To achieve a perfect circle, you can visualize its size and shape while spinning the paper as you draw. If drawing a circle proves challenging, you can employ a compass or simply trace the outline of a bowl or cup. 2) Draw Eyes: Inside the circle, draw two more circles. 3) Draw the Tear Drop: Use a blue sharpie to draw the tear drop. Leave some white for a highlight. 4) Draw the Mouth: Below the eyes, use a yellow Sharpie to draw a downward curved line that forms a frown. 5) Coloring: Color the eyes black and leave a little white for a highlight in each eye. Color the eye brows and inside of the mouth black. Color the tear drop blue, leave a little white for a highlight. Color the rest of the emoji in yellow. Remember, this is a simple representation of the emoji, and you can customize it further by adding details or shading to make it more appealing. Examples below. *Optional: Facial Lines: Add some lines near the eyes and mouth to give your emoji a more animated look. These lines can be short, curved strokes around the eyes and a couple of curved lines at the corners of the mouth. *Optional: Outline: If you want, you can outline the emoji with a darker color to make it stand out. Don't forget to Like, Comment, and Follow! Practice and creativity will help you perfect your emoji drawing! Thanks for watching, and be sure to follow for more enjoyable and creative drawing tutorials! #EmojiArtTutorial, #StepByStepDrawing, #SadEmojiGuide, #CreativeSketching, #adiyemojishow more

EXCUSE ME?? IQuest raised a 320B model from its... very first token, then gave it over a million exams with three proctors on every single one the exams are real executable containers. one check runs while the environment gets prepped, one while the code executes, and a full trajectory audit after. if the model tries to peek at hidden tests, it gets flagged, so every pass it learns from is earned it's called IQuest-Q1, an open model built to live in your terminal → 15B active out of 320B, only 8 of 256 experts per token → 29T training tokens, context stretched 32K → 128K → 512K → SFT, RL in real environments, then multi-teacher distillation (MOPD) → runs inside Claude Code, Codex and other agent scaffolds my favorite speed trick: an MTP layer gets reused as a drafter that guesses the next tokens, and the main model checks them. long sessions get way cheaper on the same parameter budget the team calls this an early release. a first model with training this strict makes me want to see the second one try it:show more

One idea, a playable game. Nex-N2.5 Pro drove the... whole thing rough idea →2D sketch →Blender 3D scene →finished game. It wasn't prompting from a distance it opened the tools, watched what changed on screen, and kept going the demos keep landing on the same question: can it actually use a computer? not generate an image of a kitchen call Blender MCP, build the kitchen, render it, read the result. Not describe a CAD part script it, adjust parameters, hit an export wall, switch to the GUI, hand off the drawing try it free on openRouter for a limited time: #NexN2 #Blender #ComputerUse #OpenRoutershow more

HydraFusion Explained. Part I: How does the Copilot engine... know what to optimize for? Your prompt is evaluated across 4 dimensions: ➡ Does it require deep reasoning? (aka. reasoning depth) ➡ Is it a sophisticated problem? (aka. code generation complexity) ➡ Is it untangling a complicated mess? (aka. debugging difficulty) ➡ Is it dominated by tool-use? (aka. tool orchestration needs) Based on this evaluation, a HyDRA score is assigned to determine the capability profile your task needs the most and to establish a quality bar. Part II: How does it choose a model? Note: It doesn' t pick one model to handle the entire job e2e, (that's Auto mode). Instead, it selects 1 of 3 execution workflows and assigns the best model at different stages based on the HyDRA score: 1️⃣ Single ⚙️ How it works: A single model completes the task from start to finish. ⚖️ Rationale: The task comfortably meets the quality bar with one model. Multi-model orchestration would add latency and cost with no meaningful quality gain. 2️⃣ Cascade ⚙️ How it works: A lightweight, cost-efficient model generates the solution. This draft is evaluated against a quality gate and if it falls short of the quality bar, the entire task escalates to a stronger, frontier model. ⚖️ Rationale: Only bring in the big guns when there is concrete evidence that a lightweight model won't meet the quality threshold. 3️⃣ Critique ⚙️ How it works: A lightweight model drafts the initial code and tool interactions. An independent, read-only frontier model reviews that draft and provides feedback. The original lightweight model then performs any targeted revision(s) before the final response is sent to the user. ⚖️ Rationale: Writing code (output tokens) is expensive while reviewing code (input tokens) is cheap. Instead of incurring the cost of a powerhouse writing hundreds of lines from scratch, a cost-efficient model writes the first draft, and the frontier model just reviews it and points out fixes. HydraFusion is available in experimental preview on the GitHub Copilot CLI: /experimental on, /model and select Hydrafusion (Research Preview)show more

Someone used Claude Code with an open-source Blender MCP... addon to create most of the 3D assets for a fishing game. → A single Claude Code session controlled both Blender and Unity through the Model Context Protocol → The developer's case study describes a 40-part, 42-bone crab model created in 53 minutes → Claude rendered images from multiple angles so the developer could review and give feedback → The MCP for Blender addon is MIT-licensed and also works with Codex, Cursor and other AI tools Repo:show more

this is f*cking gold Google engineers explained how to... make AI rewrite an agent’s system prompt against failing tests. a failed check becomes the next repair job. the regression suite watches for whatever that repair breaks. even the instructions become something you can test and improve. Agent = Model + Harness. the independently compiled page here maps the broader system into six parts: guides carry project rules, constraints and lessons from past failures > sensors check the work through tests, linters and validators > the loop runs the task, checks the result, retries within limits and escalates > memory preserves state, artifacts and decisions across runs > permissions control tools, writes and actions requiring approval > observability records what happened, what it cost and where it failed an agent changes a build file and announces “done.” the check looks for evidence that it actually ran the validator. if that behavior is missing, you have a specific failure to target. adjust the instructions. rerun the evaluations. check whether the improvement holds without breaking existing behavior. now a prompt change has a test history. a recurring mistake has a regression check. the next model upgrade has something concrete to pass. bookmark the diagram. give “done” a test it has to pass.show more

How to Draw a Playful Emoji 😝/ Excited, Fun,... Happy, Hilarity Emoji The 😝 emoji is often used to represent a playful or mischievous expression. It typically conveys a sense of fun, silliness, or jest in a message or conversation. Creating a drawing of the playful emoji 😝 can be fun. Here's a step-by-step guide using "V" as a reference for the eyes: Materials: Black, Red, and Yellow Sharpie Step 1) Draw the Face: To achieve the face we need to draw a perfect circle. You can trace an object that has the shape of a circle, like a plastic cup. To free-hand draw a circle follow these directions. If tracing a circle or using a drawing compass skip ahead to Step 4. Step 2) Visualize: Try to visualize the circles shape and size. Visualization always helps me draw. Step 3) Drawing a Circle Face Free-Hand: Use your middle finger as a pivot point just as you would with a drawing compass. Adjust the distance between your middle finger and the pencil being held. If the pencil is close to your middle finger you will get a small circle. If the pencil is held further from your middle finger pivot point then you draw a larger circle. We will need a large circle for this drawing. Be sure to hold your middle finger down loosely enough for the paper to spin easily, but firmly enough so that the paper doesn't slip away. Once in position without touching the pencil to the paper try spinning the paper to make sure you have the right toughness and the right feel. Once you are satisfied you can begin drawing your perfect circle for the face. Simply make contact with the pencil to the paper while keeping your middle finger in position and spinning the paper. Vola! A perfect circle! *note: I like to leave the paper flat while spinning it. However, for beginners, It can help to grab a corner of the paper while spinning it. Whatever is more comfortable for you. Step 4) Draw the Eyes: To create the eyes, start by drawing two inverted "V" shapes with the points facing towards each other. These "V's" should be positioned on their sides. Step 5) Draw the Mouth: Below the eyes, use a yellow Sharpie to draw a curved line that forms a smiling mouth. You can leave a spot open for the tongue or just color through it later with the red. It covers the yellow fine. Extend the curve slightly towards the sides to create a wide smile. Draw a tongue slightly left. It's easy two parallel lines that meet with a curve at the end. Step 6) Coloring: Color the eyes, and inside of the mouth black. Color the tongue red. *Optional, you can also out line the tongue in orange for an extra effect. Color the rest of the emoji in a bright, happy color like yellow. *Optional: Inside each "V" shape, draw a small circle for the pupils. Shade the rest of the eye except for the pupils to give them depth. *Optional: To make the eyes stand out, you can add highlights to the eyes with a white gel pen or by leaving small white areas in the pupils. Remember, practice makes perfect, so don't be discouraged if your first attempt isn't exactly how you want it. You can always try again until you're satisfied with your playful 😝 emoji. Good luck! Please like ❤️ and Follow! #EmojiArtTutorial, #StepByStepDrawing, #PlayfulEmojiGuide, #ExcitedEmoji, #DIYEmojiDrawingshow more

Blender just became a prompt box. With Kimi K3... connected through Blender MCP, you can describe a scene like this in plain English and let the model handle the ugly part: terrain, buildings, lighting, materials, camera movement, animation, and the Python scripts holding everything together. The interesting part is not the first render. Kimi can inspect the result, notice that the camera clips through a tree or the city looks suspiciously like plastic, then edit the actual Blender scene and render it again instead of restarting from zero. You still need taste, because “make it cinematic” remains one of humanity’s least useful instructions. But the distance between an empty Blender file and a fully editable 3D world just got embarrassingly small. A few years ago, creating this meant weeks of modeling, scripting, lighting, and animation. Now you can describe the world, watch Kimi build it, and spend your time fixing the final 10% instead of manually constructing the first 90%. Kimi K3 + Blender MCP is basically text-to-3D without trapping the result inside a useless generated video. Every object, material, light, camera, and keyframe stays editable.show more

Claude Code vs Blender is getting f*cking ridiculous One... approach builds a jet engine by hand The other turns a written description into a programmable 3D scene with rotating turbines, mechanical components, realistic materials, and cinematic camera movement And the difference goes way beyond modeling speed Traditional Blender workflow: > MODEL individual mechanical components > POSITION and assemble the geometry > CONFIGURE materials, lighting, and cameras > ANIMATE every moving mechanism > REWORK the scene when specifications change Claude Code + Blender Python: > GENERATE geometry from parameters > ASSEMBLE components programmatically > CONTROL turbine rotation through variables > AUTOMATE lighting and camera movements > REBUILD variations by editing the script The interesting part isn't that AI magically replaces Blender It's that Claude Code can operate Blender through Python, turning repetitive manual work into a reproducible system Want to test the difference? Open Claude Code and ask: "Generate a Blender Python script for a detailed turbofan engine with separate compressor and turbine stages, parameterized blade counts, independent shaft rotation, metallic materials, and a cinematic camera orbit Keep the geometry modular and expose the main parameters so I can regenerate variations without remodeling everything" Blender remains the rendering engine Claude Code changes how you build and control the scene Bookmark this workflow before your next 3D projectshow more