3d Design Techniques

Big breakthrough: A few months my lab at MIT introduced SPARKS, our autonomous scientific discovery model. Since then we have demonstrated applicability to broad problem spaces across domains from proteins, bio-inspired materials to inorganic materials. SPARKS learns by doing, thinks by critiquing itself & creates knowledge through recursive interaction; not just with data, but with the physical & logical consequences of its own ideas. It closes the entire scientific loop - hypothesis generation, data retrieval, coding, simulation, critique, refinement, & detailed manuscript drafting - without prompts, manual tuning, or human oversight. SPARKS is fundamentally different from frontier models. While models like o3-pro and o3 deep research can produce summaries, they stop short of full discovery. SPARKS conducts the entire scientific process autonomously, generating & validating falsifiable hypotheses, interpreting results & refining its approach until a reproducible, fully validated evidence-based discovery emerges. This is the first time we've seen AI discover new science. SPARKS is orders of magnitude more capable than frontier models & even when comparing just the writing, SPARKS still outperforms: in our benchmark evaluation, it scored 1.6× higher than o3-pro and over 2.5× higher than o3 deep research - not because it writes more, but because it writes with purpose, grounded in original, validated compositional reasoning from start to finish. We benchmarked SPARKS on several case studies, where it uncovered two previously unknown protein design rules: 1⃣ Length-dependent mechanical crossover β-sheet-rich peptides outperform α-helices—but only once chains exceed ~80 amino acids. Below that, helices dominate. No prior systematic study had exposed this crossover, leaving protein designers without a quantitative rule for sizing sheet-rich materials. This discovery resolves a long-standing ambiguity in molecular design and provides a principle to guide the structural tuning of biomaterials and protein-based nanodevices based on mechanical strength. 2⃣ A stability “frustration zone” At intermediate lengths (~50- 70 residues) with balanced α/β content, peptide stability becomes highly variable. Sparks mapped this volatile region and explained its cause: competing folding nuclei and exposed edge strands that destabilize structure. This insight pinpoints a failure regime in protein design where instability arises not from randomness, but from well-defined physical constraints, giving designers new levers to avoid brittle configurations or engineer around them. This gives engineers and biologists a roadmap for avoiding stability traps in de novo design - especially when exploring hybrid motifs. Stay tuned for more updates & examples, papers and more details.

𝐓𝐡𝐞 𝐚𝐫𝐭 𝐨𝐟 𝐫𝐞𝐭𝐫𝐚𝐜𝐭𝐚𝐛𝐥𝐞 𝐟𝐮𝐫𝐧𝐢𝐭𝐮𝐫𝐞 𝐝𝐞𝐬𝐢𝐠𝐧 𝐢𝐬 𝐧𝐨𝐭 𝐣𝐮𝐬𝐭 𝐚𝐛𝐨𝐮𝐭 𝐬𝐚𝐯𝐢𝐧𝐠 𝐬𝐩𝐚𝐜𝐞, 𝐢𝐭 𝐢𝐬 𝐚𝐛𝐨𝐮𝐭 𝐫𝐞𝐝𝐞𝐟𝐢𝐧𝐢𝐧𝐠 𝐡𝐨𝐰 𝐚 𝐬𝐢𝐧𝐠𝐥𝐞 𝐞𝐧𝐯𝐢𝐫𝐨𝐧𝐦𝐞𝐧𝐭 𝐜𝐚𝐧 𝐚𝐝𝐚𝐩𝐭, 𝐞𝐯𝐨𝐥𝐯𝐞, 𝐚𝐧𝐝 𝐩𝐞𝐫𝐟𝐨𝐫𝐦 𝐦𝐮𝐥𝐭𝐢𝐩𝐥𝐞 𝐟𝐮𝐧𝐜𝐭𝐢𝐨𝐧𝐬 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐜𝐨𝐦𝐩𝐫𝐨𝐦𝐢𝐬𝐢𝐧𝐠 𝐜𝐨𝐦𝐟𝐨𝐫𝐭, 𝐚𝐞𝐬𝐭𝐡𝐞𝐭𝐢𝐜𝐬, 𝐨𝐫 𝐮𝐬𝐚𝐛𝐢𝐥𝐢𝐭𝐲. 🏠 From an architectural and interior design perspective, the demonstrated arrangement represents an advanced space-transforming solution where integrated storage systems, concealed beds, foldable workstations, pull-out seating modules, modular shelving units, and custom joinery are intelligently combined to create highly adaptable living environments. The design achieves exceptional spatial efficiency while preserving visual harmony through coordinated finishes, concealed hardware, integrated lighting systems, and seamless circulation planning, resulting in a refined, modern, and clutter-free interior experience. 📌 𝐒𝐩𝐚𝐜𝐞 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧 & 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐥𝐞𝐱𝐢𝐛𝐢𝐥𝐢𝐭𝐲: ✓. Multiple functions within one space. ✓. Reduced permanent furniture footprint. ✓. Adaptive day-to-night usability. ✓. Maximized usable floor area. 📌 𝐈𝐧𝐭𝐞𝐫𝐢𝐨𝐫 𝐃𝐞𝐬𝐢𝐠𝐧 & 𝐀𝐞𝐬𝐭𝐡𝐞𝐭𝐢𝐜 𝐄𝐱𝐜𝐞𝐥𝐥𝐞𝐧𝐜𝐞: ✓. Seamless concealed furniture integration. ✓. Coordinated finishes and material harmony. ✓. Clean modern visual appearance. ✓. Clutter-free organized living environment. 📌 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 & 𝐂𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐏𝐫𝐞𝐜𝐢𝐬𝐢𝐨𝐧: ✓. Reinforced structural support provisions. ✓. Heavy-duty telescopic runner systems. ✓. Concealed hinges and locking mechanisms. ✓. Precision guide-track installation. 📌 𝐅𝐮𝐧𝐜𝐭𝐢𝐨𝐧𝐚𝐥𝐢𝐭𝐲 & 𝐔𝐬𝐞𝐫 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞: ✓. Enhanced storage capacity achieved. ✓. Smooth and safe operation. ✓. Improved accessibility and circulation. ✓. Flexible lifestyle accommodation. 📌 𝐒𝐮𝐬𝐭𝐚𝐢𝐧𝐚𝐛𝐢𝐥𝐢𝐭𝐲 & 𝐋𝐨𝐧𝐠-𝐓𝐞𝐫𝐦 𝐕𝐚𝐥𝐮𝐞: ✓. Optimized resource utilization. ✓. Reduced material consumption. ✓. Supports compact living solutions. ✓. Increased property market value. 📌 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐎𝐮𝐭𝐜𝐨𝐦𝐞: ✓. Intelligent space transformation. ✓. Advanced joinery integration. ✓. Enhanced functional efficiency. ✓. Future-ready living environment.

🔧 From Casting to Precision Machining: The Journey of Heavy Industrial Gears Ever wondered how large-scale industrial gears are manufactured? This video walks through the complete process — starting from wooden pattern making and sand casting, to precision machining on vertical & horizontal milling machines, vertical lathes, and horizontal lathes. Key Highlights: ⚙️ Pattern & Moulding: Wooden moulds prepared → sand packed around → molten metal poured to form the raw gear blank. ⚙️ Casting Materials: High-strength alloys for durability, wear resistance, and load-bearing capability. ⚙️ Machining Processes: Vertical & Horizontal Milling → Cutting gear teeth with precision. Turning (Vertical & Horizontal Lathes) → Achieving roundness, dimensional accuracy, and surface finish. ⚙️ Manufacturing Accuracy: Tolerances are held to microns, ensuring gears meet ISO/AGMA standards for performance and reliability. ⚙️ Applications: Heavy-duty gears like these power industries such as steel, cement, mining, and energy. Manufacturing isn’t just about shaping metal — it’s about precision engineering, material science, and reliability under extreme loads. 🔍 This process showcases how traditional casting methods integrate with modern machining techniques to deliver high-performance industrial gears that keep industries running. #Manufacturing #GearManufacturing #Casting #CNC #Milling #Turning #PrecisionEngineering #IndustrialMachinery #MechanicalEngineering #SmartManufacturing #HeavyIndustry

An abandoned basketball court reimagined into a modern loft — optimized using AI-driven design and data. Would you live here? This transformation isn’t just visual. AI-based space optimization tools were used to model how people actually live, move, and use space: 1,000+ layout simulations evaluated for circulation efficiency, light access, and privacy 20–30% reduction in wasted space by optimizing zoning and vertical volume A raised bedroom increased usable floor area by ~15% without expanding the footprint AI daylight simulations improved natural light penetration by 25–35% across the day Storage and furniture placement optimized to reduce movement friction by up to 40% The outcome: A space that feels significantly larger, brighter, and calmer — without adding square meters. Why this matters: In dense cities, every m²/foot² saved can reduce construction cost by 8–12% AI-optimized layouts show 10–20% higher long-term livability scores compared to traditional designs Adaptive reuse projects like this can cut embodied carbon by 50–70% versus new builds This is what happens when AI meets architecture: Less waste. Better living. Smarter use of what already exists. #AI #Architecture via @alot_design #SpaceOptimization #GenerativeDesign #AdaptiveReuse #SustainableDesign #FutureOfLiving #UrbanInnovation

This is how AI de novo discovery should be used! AI discovery of novel binders (mAbs, mini-proteins etc) has made huge strides but when you cut through the hype the realty is most reports don't offer something we can't already do. We now have liability free libraries enabling discovery of developable, low pM human antibodies in a few months. AI design papers tend to focus on well characterised proteins like RBD, EGFR, PD1. Interesting, and this is early days for AI, but if it's really going to disrupt biologics discovery it needs to go beyond what we can already do with antibodies. Intrinsically disordered proteins and peptides (IDPs) have sequences that lack 3D structure. IDPs play key roles in biology but a lack of defined structure and sequence variability makes targeting them with mAbs or other binders extremely challenging. Enter David Baker and colleagues. Rather than viewing IDP conformational heterogeneity as a hindrance, they saw it as an advantage. Folded proteins only allow a few optimal binding solutions. IDPs can adopt a wide variety of conformations and a binder can actively induce an optimal fit. So they set out to develop an in silico design pipeline to create specific high affinity binders to IDPs. They started by designing repeating units that could wrap around peptides. These binding pockets were designed to interact with both amino acid side chains and peptide backbone for structural specificity. Basic scaffolds were refined and recombined so they could recognise a wide range of motifs. The result was a library of diverse templates that bind to intrinsically disordered peptides. Peptides of choice then undergo 'computational threading' to determine which of the protein templates in the best binder. Think of it as an in silico phage display library for IDPs. From here the binding protein can be further refined for greater affinity and specificity. The team successfully designed binders for 39 out of 43 tested targets, including 18 synthetic peptide sequences and 21 therapeutically relevant IDPs - this included 3 where no good antibodies have ever been reported! Most designs exhibited picomolar to nanomolar affinity and high specificity. Crystallography and NMR confirmed that the designed binders induce the disordered targets to adopt specific, often non-native, conformations upon binding. This appears to be a big step forward in targeting IDPs. As well as obvious potential in therapeutics, such binders could be highly useful in imaging, proteomics and sequencing. More generally, this is the kind of space where we should be pushing to utilise AI, opening up biology that is challenging, sometimes impossible, with antibodies and other biologics. Link to paper in comments. ----- I'm Ian, I post about antibody engineering, recombinant proteins and my journey to bootstrap Gamma Proteins into a leading supplier of Fc receptors. If you like my content please reshare with your network and follow me to see more.

Streaming 3D reconstruction is fundamentally a memory problem. How do you map a massive, multi-room environment without blowing up your compute budget as the sequence gets longer? Lingbo-Map just introduced a highly elegant architectural solution to this exact bottleneck: Geometric Context Attention (GCA). Instead of brute-forcing the entire scene history into memory, GCA splits the streaming state into three lightweight buckets: an anchor for global coordinate grounding, a local reference window for dense geometry, and a compressed trajectory memory. By squashing the full sequence history into compact per-frame tokens, the memory and compute requirements remain nearly constant. Running through a DINO backbone, the pipeline actively predicts camera poses and depth maps at ~20 FPS—even on continuous 10,000+ frame sequences. This is how you scale real-time spatial computing and large-scale digital twins without needing infinite VRAM. Models: https://lnkd.in/dxY7D4Ar Project page: https://lnkd.in/dKRUEQaq Code: https://lnkd.in/dXQSJB7u Paper: https://lnkd.in/diPQk3Ki #SpatialComputing #3DReconstruction #ComputerVision #MachineLearning #SLAM #DevRel

Want to lose players? Ignore how their brains work. Frustrated players don’t stick around. Why? The design doesn’t match how we think. Fix it with these UX principles. 𝟭. 𝗣𝗿𝗼𝘅𝗶𝗺𝗶𝘁𝘆 The Brain: ↳ We group nearby objects together. [UX in Action] • Group related info in the HUD (health, ammo, abilities). • Organize menus logically - e.g., defense skills in one column, offense in another. Example: Assassin’s Creed Syndicate groups contextual actions for clarity. Tip: Space = clarity. Clutter = confusion. 𝟮. 𝗦𝗶𝗺𝗶𝗹𝗮𝗿𝗶𝘁𝘆 The Brain: ↳ We link objects that look alike. [UX in Action] • Color-code items with similar functions (e.g., health packs, weapons). • Use consistent shapes and visuals for recurring gameplay elements. Example: Overwatch health packs are green (heal) or blue (shields) - instant recognition. Tip: Consistency builds trust. Random changes destroy it. 𝟯. 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗶𝘁𝘆 The Brain: ↳ We follow lines and curves naturally. [UX in Action] • Use roads, trails, or subtle environmental cues to guide players to objectives. • Skill trees should flow visually - connected lines = unlock progression. Example: Journey uses curved dunes to nudge players without obvious prompts. Tip: Guide, don’t force. Let the world “pull” players forward. 𝟰. 𝗖𝗹𝗼𝘀𝘂𝗿𝗲 The Brain: ↳ We fill in gaps to see the whole picture. [UX in Action] • Use outlines to suggest symbols without cluttering the interface. • Design puzzles that let players solve the gaps (e.g., bridges, maps). Example: Breath of the Wild uses glowing shrines to tease exploration. Tip: Less is more. Let players’ curiosity fill in the blanks. 𝟱. 𝗙𝗶𝗴𝘂𝗿𝗲-𝗚𝗿𝗼𝘂𝗻𝗱 The Brain: ↳ We separate objects from their background [UX in Action] • Use contrast to make interactive elements pop (e.g., glowing loot, enemy outlines) • Keep non-interactive elements subtle to avoid visual clutter. Example: Fortnite highlights loot with bright effects, making them stand out. Tip: Contrast = focus. Subtlety = immersion. 𝟲. 𝗦𝘆𝗺𝗺𝗲𝘁𝗿𝘆 𝗮𝗻𝗱 𝗢𝗿𝗱𝗲𝗿 The Brain: ↳ Symmetry feels balanced. Chaos doesn’t. [UX in Action] • Use symmetrical grids in inventories to make items easy to find. • Apply symmetry in level design for logical layouts; break symmetry to add tension. Example: Portal uses symmetrical puzzles to imply logic and balance. Tip: Symmetry = calm. Asymmetry = challenge. Use both wisely. 𝟳. 𝗖𝗼𝗺𝗺𝗼𝗻 𝗙𝗮𝘁𝗲 The Brain: ↳ Moving objects seem connected. [UX in Action] • Groups of enemies moving together signal coordinated threats. • Use synchronized motion (swaying ropes or flashing lights) to guide attention. Example: Uncharted uses environmental motion to point out climbable paths. Tip: Movement = meaning. Use it to guide, not distract.     **** Looking for more insights? 🔴 Start with my book https://lnkd.in/euQYayqc 10 more tips & actions in the comments 👇

Can you buy a phone case made from a sustainable plastic? In a paper published in Nature Sustainability, researchers report catalyst-free, melt polymerization process of dimethyl glyoxylate xylose, a stabilized carbohydrate derived from agricultural waste with an impressive 97% atom efficiency. This synthesis yields amorphous polyamides exhibiting performance levels akin to fossil-based semi-aromatic alternatives. Despite the carbohydrate core, these materials maintain their thermomechanical properties across multiple cycles of high-shear mechanical recycling, and they are also amenable to chemical recycling. Techno-economic and life-cycle analyses indicate that the selling prices of these polyamides could approach those of nylon 66, while concurrently reducing global warming potential by up to 75%. The potential applications for these innovative polyamides are vast, ranging from automotive parts to consumer goods.   Link to the Nature Sustainability paper is given in the comment section.   Image Credit: Lorenz Manker/EPFL Image Caption: An iPhone case 3D printed with the sustainable polyamide material

Ever feel stuck trying to pick the "right" design problem to solve? You’re not alone. Most designers rush to solutions before they even know if they’re solving the right thing. Here’s how I find the best design problems- and how you can too: • 𝗦𝘁𝗮𝗿𝘁 𝘄𝗶𝘁𝗵 𝗿𝗲𝗮𝗹 𝘂𝘀𝗲𝗿𝘀, 𝗻𝗼𝘁 𝗴𝘂𝗲𝘀𝘀𝗲𝘀. Watch how people actually use your product. Don’t just listen to what they say- see what they do. Dive deep into how they do things right now. You’ll spot hidden pain points and strange shortcuts surveys miss. • 𝗞𝗲𝗲𝗽 𝗮𝘀𝗸𝗶𝗻𝗴 “𝘄𝗵𝘆”. Don’t settle for the first answer. Dig deeper. The best problems hide beneath surface complaints. Asking “why” helps you identify the real barriers. • 𝗗𝗲𝗳𝗶𝗻𝗲 𝘁𝗵𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺 𝗰𝗹𝗲𝗮𝗿𝗹𝘆 𝗯𝗲𝗳𝗼𝗿𝗲 𝗷𝘂𝗺𝗽𝗶𝗻𝗴 𝘁𝗼 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝘀. Write it simply. No jargon, no features. Just what’s broken and for whom. If anyone can understand your problem statement, you’re on the right track. • 𝗟𝗼𝗼𝗸 𝗳𝗼𝗿 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀, 𝗻𝗼𝘁 𝗼𝗻𝗲-𝗼𝗳𝗳𝘀. A good design problem isn’t just a bug- it’s a pattern. If the same struggle shows up in different places or users, you’ve found something worth fixing. • 𝗧𝗵𝗶𝗻𝗸 𝗯𝗲𝘆𝗼𝗻𝗱 𝘁𝗵𝗲 𝗯𝗿𝗶𝗲𝗳. Sometimes the client’s request is just part of the story. Step back. Is there a deeper, bigger problem you can solve? The best designers create solutions people didn’t even know they needed. Solving small, obvious problems is easy. Spotting the invisible problems- the ones that change the whole experience- is what makes you stand out. When you focus on finding the right problems, not just any problem, that’s when you start to create a real impact. Follow for more practical design insights you can use everyday.

𝐄𝐯𝐞𝐫𝐲𝐭𝐡𝐢𝐧𝐠 𝐈𝐬 𝐔𝐧𝐝𝐞𝐫 𝐑𝐞𝐩𝐚𝐢𝐫 – 𝐂𝐢𝐭𝐢𝐞𝐬, 𝐂𝐨𝐦𝐩𝐚𝐧𝐢𝐞𝐬, 𝐚𝐧𝐝 𝐌𝐚𝐲𝐛𝐞 𝐄𝐯𝐞𝐧 𝐔𝐬 ⇢ Cities are under repair. White-topping, metro work, new flyovers, endless roadblocks. ⇢ Companies are under repair. Restructuring, efficiency tools, leadership changes, endless meetings. ⇢ And somehow, life still feels stuck in traffic. Last week, in Mumbai, I ran a Design Thinking workshop. Students walked in expecting creativity lessons. They walked out questioning everything they thought they knew about problem-solving. Because three-fourths of the day was spent just defining the problem. ⇢ Ever walked on a footpath that disappears? ⇢ Ever stood at a train door, calculating survival if you fall? ⇢ Ever had a bus refuse to stop because it was “too crowded”? Everyone dreams of seamless transport. But in reality? Ten kilometers in ten minutes? More like ten kilometers in an hour. ⇢ The ideal world? We solve traffic with flying cars. ⇢ The wishful world? One app fixes everything. ⇢ The real world? A ten-year metro project causes more traffic than it solves. That’s when it hit them—this isn’t just about Mumbai. It’s about every broken system they’ll face in their careers. 𝐓𝐡𝐞 𝐒𝐚𝐦𝐞 𝐌𝐞𝐬𝐬, 𝐄𝐯𝐞𝐫𝐲𝐰𝐡𝐞𝐫𝐞 ⇢ Cities: We build flyovers, yet traffic shifts elsewhere. ⇢ Companies: More tools for efficiency, yet more time wasted on dashboards. ⇢ Leadership: Launch new projects, but never fix existing chaos. A student asked me, "Why do good ideas die so fast?" Because decisions are made without understanding real people. ⇢ What if policies were citizen-first, not contractor-first? ⇢ What if HR actually put humans first? ⇢ What if leadership solved problems instead of just making changes? The Moment That Changed Everything As we wrapped up, one student, frustrated yet energized, said: "𝐖𝐞 𝐤𝐞𝐞𝐩 𝐟𝐢𝐱𝐢𝐧𝐠 𝐭𝐡𝐢𝐧𝐠𝐬. 𝐁𝐮𝐭 𝐚𝐫𝐞 𝐰𝐞 𝐟𝐢𝐱𝐢𝐧𝐠 𝐭𝐡𝐞 𝐫𝐢𝐠𝐡𝐭 𝐭𝐡𝐢𝐧𝐠𝐬?" That Hit Hard! Because whether it's a city, a workplace, or a leadership decision—we don’t need more solutions. We need better-designed ones. And that’s when they realized: 𝘋𝘦𝘴𝘪𝘨𝘯 𝘛𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘪𝘴 𝘯𝘰𝘵 𝘢𝘣𝘰𝘶𝘵 𝘤𝘳𝘦𝘢𝘵𝘪𝘯𝘨 𝘴𝘰𝘭𝘶𝘵𝘪𝘰𝘯𝘴. 𝘐𝘵’𝘴 𝘢𝘣𝘰𝘶𝘵 𝘴𝘰𝘭𝘷𝘪𝘯𝘨 𝘵𝘩𝘦 𝘳𝘪𝘨𝘩𝘵 𝘱𝘳𝘰𝘣𝘭𝘦𝘮𝘴. Students walked in expecting design lessons. They walked out seeing the world differently. And here’s the thing, students from past batches still call me with ideas they want to solve. That’s the impact of Design Thinking done right. A big shoutout to KIRAN Dalani and Shobha Venkatesh for trusting me for years. These conversations are the reason I keep coming back. Now, Over to You What’s a problem you’ve seen that’s always “under repair” but never really fixed? Drop your thoughts below. Let’s discuss. PGDPMEM #designthinking #leadership #humancentereddesign #fixtherightthings