AR:One

I realised recently that the time I was spending sharing my ideas was actually strangling the sharing of ideas themselves. In this BrainStream, I'm opening up about why I'm working to automate my entire production pipeline—from transcripts to clips— to keep sharing. I think we're entering an era where 'janking' together AI tools like Claude Code and Remotion isn't just a hack; it's the only way to keep up with the ROI of our own thoughts. I wonder if the future of the UI isn't just talking to our computers, but having them understand the visual and emotional context of our work before we even ask. Timestamps(0:00) The Guatemala Vision Pro Backlog (2:15) When the ROI of Sharing Doesn't Make Sense (4:10) From 2017 Manual Edits to AI Pipelines (6:20) Automating the 'Boring Stuff': Clips & Captions (8:10) The Post-Siri World: OpenClaw & Agentic Filesystems Listen OnIf you enjoyed this episode, you can listen to more of my brainstreams on Spotify, YouTube, or Apple Podcasts. Check out my website for more insights: https://avrahamrask.in/podcast

We’re finally breaking free from the 1980s desktop paradigm and moving into a world where creation isn’t tied to a workstation. I’m diving into how I finally cracked the code on local automation for the BrainStream, bringing us closer to a future of conversational agents that actually understand and build alongside us. From my early work on the Whisper project to the current shift in spatial computing, we’re exploring how we can stop being tethered to a desk and start leveraging high-fidelity AI collaboration wherever we go. Timestamps[0:00] From GUI to Conversational OS [1:36] The Whisper Vision: Untethered AI [3:12] The High Cost of Manual Friction [4:30] Custom Pipelines Over SaaS Bloat [6:20] Local Video Clipping with Whisper JSON [8:10] Iterative Media & Generative Assets Listen OnIf you enjoyed this episode, you can listen to more of my brainstreams on Spotify, YouTube, or Apple Podcasts. Check out my website for more insights: https://avrahamrask.in/podcast

The velocity of innovation right now is insane—we’re seeing a year’s worth of progress every week—and the only way to keep up is to automate the friction out of our systems. I’ve finally dialed in a pipeline that handles the heavy lifting of post-production and distribution with a single click, freeing me up to dive deeper into the high-stakes security projects I’ve been teasing. This episode is a direct look at how I’m using AI to reclaim my time, moving away from manual content management and back toward pure insight and execution. If we're going to build the future, we can't afford to be slowed down by the logistics of the present. TIMESTAMPS:0:00 | Navigating the AI Acceleration Curve 1:45 | Why Content Friction Stalls Big Ideas 3:20 | The Utility of the Spoken Word 5:10 | Solving Local vs. Cloud Friction 6:55 | Video as Code: The Remotion Shift 8:30 | Closing the Agent-Driven Loop LISTEN ON Spotify: https://open.spotify.com/show/0gyQydQ9h5PM2gGUWy1PfC YouTube: https://youtube.com/playlist?list=PLifoYer83q8ACtYWCtjhoOHGmfslydLM7&si=yKhmWU6J9t6j9USF Apple Podcasts: https://podcasts.apple.com/us/podcast/id1726877985 Website: https://avrahamrask.in/podcast

In this year-end Brainstream, Avraham revisits a 2018–2019 video exploring how augmented reality and AI could transform everyday problem solving. Using the example of fixing a broken fridge, he unpacks multimodal AI—vision, sound, and conversation working together—and reflects on how concepts from seven years ago are becoming increasingly practical today. This episode also considers the evolving relationship between humans and AI in collaborative problem solving. TL;DR A seven-year-old video predicting AI-assisted, AR-driven home repairs highlights how multimodal AI—integrating vision, sound, and conversation—can empower humans to solve problems collaboratively without experts or cloud dependency. 🎧 Listen on Spotify | YouTube | Apple Podcasts Listen to the full episode and explore more Brainstream → https://avrahamraskin.com/podcast

A quiet rumour about OpenAI tapping into Apple Health sparks a deeper question: what would a truly private, on-device health intelligence actually look like? Listen on Spotify, YouTube, Apple Podcasts More episodes → https://avrahamraskin.com/podcast Timestamps 00:00 | The Rumour About OpenAI And Apple Health 01:06 | Why Access To Raw Health Data Actually Matters 01:45 | The Privacy Problem With Cloud-Based LLMs 02:26 | The Case For A True On-Device Reasoning Model 03:12 | Hardware Limits And Why Models Must Shrink 04:26 | What A Smarter Siri Should Really Be 05:14 | Health Metrics, Trends, And Real Coaching 06:24 | The Missing Link: Nutrition Data 07:12 | Rumours Of Apple HealthPlus 08:02 | What Real AI Coaching Should Feel Like 09:07 | Integrating Sleep, Training, Journaling, And Goals 09:48 | The Vision: A Private, Personal, On-Device Coach

Most security systems still behave like they did 20 years ago—reactive, limited, and blind to the context hidden inside their own recordings. In this Brainstream, we explore why the real frontier in security isn’t better alerts or higher-resolution cameras, but AI systems that can learn a site’s patterns, behaviours, anomalies, and risks over months of recorded footage. This episode outlines the shift from “review after the incident” to “predict before it happens,” and why the intelligence trapped inside our footage is the most valuable, unused asset in modern security. TL;DR Security cameras shouldn’t just replay the past—they should understand it. When indexed, analysed, and contextualised, months of footage can power predictive, site-specific intelligence far beyond traditional monitoring. 🎧 Listen on ⁠Spotify, ⁠YouTube⁠, ⁠Apple Podcasts⁠ 🔗 More episodes → https://avrahamraskin.com/podcast Timestamps 00:00 | Opening: Why talk about the future of security 00:05 | Why this topic needs multiple videos 00:08 | A new product direction after years in the field 00:19 | The core problem: cameras are reactive 00:26 | Footage as an investigative tool, not a live one 00:34 | Tools like BriefCam and condensed investigations 00:51 | The inevitability of deep pattern analysis 01:17 | Rethinking what recorded footage really contains 01:26 | On-site storage vs cloud motion clips 01:48 | Why modern systems rarely store “everything” 02:14 | The hidden value inside long-term footage 02:27 | Thought experiment: downloading 6 months of footage into a guard 03:06 | Scale: 25–100 cameras, months of data 03:25 | What context a human misses vs what the data contains 03:58 | Reviewing footage: hours, days, weeks 04:25 | Pattern detection after the fact 04:54 | The industry’s stuck in reactive mode 05:02 | Moving from reactive to predictive 05:17 | Connecting dots before the incident 05:24 | Trends, anomalies, and site-specific patterns 05:34 | What good security guards actually do 06:00 | Knowing who belongs and who doesn’t 06:13 | Cameras should be able to learn the same 06:22 | Context → patterns → prediction 06:34 | Generations of camera evolution 07:00 | Smart detections: person, car, face, plate 07:14 | More granular detection: clothing, colours, models 07:36 | Natural-language retrieval: next-generation search 07:56 | But still mostly reactive 08:03 | True intelligence: learning the site itself 08:12 | Threat assessment powered by context 08:26 | The massive, untapped value in indexed footage 08:51 | Behaviour understanding vs object detection 09:04 | AI as a security operator/assistant 09:14 | Cameras becoming proactive 09:20 | Future episodes: alarms, sensors, monitoring 09:33 | Industry progress & uneven advancement 09:42 | Why pattern understanding changes everything 09:57 | Closing: A new era is coming

In this BrainStream, I explore why we’re on the edge of a generational shift in how properties are secured. Not just sensors. Not just cameras. A true, always-awake operator built from VLMs, re-identification, and on-prem AI. I look at Ubiquiti’s position, emerging players, and why the “virtual guard” model is no longer sci-fi but an inevitable next step. TL;DR Security is moving from alarms to an always-awake, property-aware AI operators that verifies, learns, and predicts. 🎧 Listen Now at Spotify, YouTube, or Apple Podcasts → More at: https://avrahamraskin.com/podcast Timestamps 00:00 | Why I Had to Record One More 00:21 | The Ubiquiti/UniFi Fascination 01:31 | The “Ultimate Operator” Concept 02:20 | Parameters → Description: A Real Turning Point 03:21 | Teaching an AI the Property (The Guard Analogy) 04:41 | From Virtual Guards to Site-Aware Intelligence 05:22 | Alarm Monitoring: The Missing Link 06:13 | Camera Verification and VLM Reasoning 08:48 | Prediction Instead of Reaction 09:51 | Closing the Loop: Where This Is Heading #Ubiquiti #UniFi #VideoOperator #VLM #Re-ID #Alarm #Verification #PredictiveSecurity #On-Prem AI #ComputerVision #Security #Future

A concise, investigative tour of how security video evolved from passive cctv to intelligent, searchable footage powered by local ai and video-language models. I maps the technical lineage-motion sensing, smart detections, face and plate id, the “AI Key,” and scene-level vlm search-and explain why pattern discovery at scale is the next operational leap for site security and investigations. “video that used to be passive now becomes a searchable narrative.” 🎧 listen on spotify, youtube, apple podcasts 🔗 more episodes → https://avrahamraskin.com/podcast tl;dr security cameras have graduated from passive recorders to active, searchable sensors. video-language models (vlms) and local llm-like agents enable natural-language scene search and condensed pattern visualisations-powerful for investigations but constrained today by compute and edge deployment. the next frontier is real-time, site-wide pattern detection running at the edge. timestamps 00:00 | introduction and context 00:23 | the evolution: cctv → motion → smart detections 01:56 | face detection, license plates, and granular id 02:19 | the “ai key”: local llm-style analytics (what it adds) 03:35 | video-language models: frame description → search 05:03 | practical investigative tools and scene search examples 06:03 | pattern discovery: briefcam and condensed timelines 07:40 | limitations today: compute, edge, and the next step 09:56 | closing thoughts and what’s next

Most security systems still behave like they did 20 years ago-reactive, limited, and blind to the context hidden inside their own recordings. In this Brainstream, we explore why the real frontier in security isn’t better alerts or higher-resolution cameras, but AI systems that can learn a site’s patterns, behaviours, anomalies, and risks over months of recorded footage. This episode outlines the shift from “review after the incident” to “predict before it happens,” and why the intelligence trapped inside our footage is the most valuable, unused asset in modern security. TL;DR Security cameras shouldn’t just replay the past-they should understand it. When indexed, analysed, and contextualised, months of footage can power predictive, site-specific intelligence far beyond traditional monitoring. 🎧 Listen on ⁠⁠Spotify⁠, ⁠⁠YouTube⁠⁠, ⁠⁠Apple Podcasts⁠⁠ 🔗 More episodes → ⁠https://avrahamraskin.com/podcast⁠ Timestamps 00:00 | Opening: Why talk about the future of security 00:05 | Why this topic needs multiple videos 00:08 | A new product direction after years in the field 00:19 | The core problem: cameras are reactive 00:26 | Footage as an investigative tool, not a live one 00:34 | Tools like BriefCam and condensed investigations 00:51 | The inevitability of deep pattern analysis 01:17 | Rethinking what recorded footage really contains 01:26 | On-site storage vs cloud motion clips 01:48 | Why modern systems rarely store “everything” 02:14 | The hidden value inside long-term footage 02:27 | Thought experiment: downloading 6 months of footage into a guard 03:06 | Scale: 25–100 cameras, months of data 03:25 | What context a human misses vs what the data contains 03:58 | Reviewing footage: hours, days, weeks 04:25 | Pattern detection after the fact 04:54 | The industry’s stuck in reactive mode 05:02 | Moving from reactive to predictive 05:17 | Connecting dots before the incident 05:24 | Trends, anomalies, and site-specific patterns 05:34 | What good security guards actually do 06:00 | Knowing who belongs and who doesn’t 06:13 | Cameras should be able to learn the same 06:22 | Context → patterns → prediction 06:34 | Generations of camera evolution 07:00 | Smart detections: person, car, face, plate 07:14 | More granular detection: clothing, colours, models 07:36 | Natural-language retrieval: next-generation search 07:56 | But still mostly reactive 08:03 | True intelligence: learning the site itself 08:12 | Threat assessment powered by context 08:26 | The massive, untapped value in indexed footage 08:51 | Behaviour understanding vs object detection 09:04 | AI as a security operator/assistant 09:14 | Cameras becoming proactive 09:20 | Future episodes: alarms, sensors, monitoring 09:33 | Industry progress & uneven advancement 09:42 | Why pattern understanding changes everything 09:57 | Closing: A new era is coming

What if you could circle the entire Old City of Jerusalem—comfortably, accessibly, and beautifully? In this episode of Brainstreams, we explore a future-facing vision for a dedicated light rail line that loops around the Old City walls. From smart routing and grade calculations to archaeological sensitivity and pedestrian flow, this Brainstream dives deep into a generative design sprint born from both data and lived experience. TL;DR: A Jerusalem city loop light rail around all seven gates could transform access, beauty, and spiritual flow—this is the design pitch. We discuss multi-line integration (red, brown, yellow), how to preserve archaeology while opening new paths, grading challenges, and why a humble footpath + rail combo might be the most transformative layer Jerusalem’s had in decades. 🎧 Listen now on ⁠Spotify⁠, ⁠YouTube⁠, or ⁠Apple Podcasts⁠ → More at ⁠avrahamraskin.com/podcast⁠ Timestamps: 00:00 — Intro: What is the Old City Loop? 00:43 — Green space, walking path, and rail: the triple-ring vision 01:58 — The gaps in Jerusalem’s current light rail access 03:06 — Seven gates, one loop: walking through the plan 05:01 — Grades, curvature, and optimal timing 06:13 — Integrating with existing and future lines (Red, Yellow, Brown) 07:30 — One-way loop + second-direction bus support 09:23 — Accessibility at Shaar Tzion & other grading concerns 10:00 — Park & Ride potential near Damascus and Dung Gates 12:04 — New Gate tradeoffs & archaeological bridge ideas 13:06 — Solving steep terrain with design sensitivity 14:39 — Closing thoughts: Could this really happen?

What if kosher products simply revealed themselves—- guessing, no flipping, no frantic Googling? In this Brainstream, we explore a futuristic vision that’s already partially built: an augmented-reality-based kosher shopping experience. Born from the frustration of finding kosher food in Australia, the idea reimagines the process from the ground up-no lists, no scanning, just visual certainty. TL;DR: Imagine pointing your phone at a supermarket shelf and instantly seeing which products are kosher-powered by AR, crowdsourcing, and smart databases. This Brainstream lays out that vision. We also dive into the pain of local-only kosher databases, the promise of contributor modes, and how we can use computer vision, gamification, and community to create the ultimate global kosher assistant. 🎧 Listen now on Spotify, YouTube, or Apple Podcasts → More at avrahamraskin.com/podcast Timestamps: 00:00 — The AR Kosher Shopping Vision 00:49 — Growing Up Without Easy Kosher Access 02:00 — Kosher Australia App: Helpful But Limited 03:04 — The Chocolate Shelf Incident (and UX friction) 04:11 — Barcode Scanning: A Step Forward, Still Painful 05:25 — Every Country Has Its Own App (if you’re lucky) 06:03 — Why Kosher Data Shouldn’t Be Gatekept 07:00 — Introducing Contributor Mode & Crowdsourced Verification 08:13 — How OCR + Computer Vision Enable Instant Recognition 09:23 — Game Mechanics for Certifying Products 10:22 — Verification Badges & Authority Endorsements 12:01 — The Pay-It-Forward Incentive Loop for Travellers 13:03 — Making Kashrut Fun, Seamless, and Fluid 14:01 — The Auto-Scan Dream and Proximity-Based Info

Apple’s WWDC recap wasn’t just about shiny new models or flashy demos — it revealed a vision of computing where intelligence lives closer to you than ever before. In this Brainstream, I explore how the shift to lightweight, on-device AI isn’t just a technical update — it’s a philosophical shift. We touch on Apple’s missed shortcuts, the layers of Layer[1], and how user experience needs to evolve into something fluid, not fragmented. TL;DR: This episode unpacks Apple’s approach to foundation models, live transcription, node-based automation, and the conceptual gaps between their vision and where it could be going — especially in relation to LayerOS. Let’s talk interface, operating systems, and why the real future is about how intelligence flows across your tools. Listen to Layer[1] on: Website, Spotify, YouTube, Apple Podcasts Timestamps: 00:00 – Quick intro: revisiting last year’s predictions 00:12 – Apple’s new live FaceTime translation 00:34 – Transcription gaps & WhatsApp voice-to-text issues 01:54 – What SiriGPT should’ve been 02:20 – Layered apps vs. intelligent flow 03:22 – Widgets, CarPlay & Apple’s game focus 04:04 – Apple’s foundation model + Sam Altman’s logic 05:13 – Shortcut builder dreams vs. Apple’s reality 07:03 – Building layered automation with AI & prompts 08:55 – Smarter Maps: learning user behaviour 09:43 – A wish for transcription + text-to-speech everywhere 10:00 – Wrap-up & future thoughts

What happens when websites evolve into worlds? In this brainstream, we explore Apple's VisionOS updates and what they mean for the future of digital interfaces. From spatial browsing to the beginnings of a 3D retail internet, Apple’s slow but deliberate steps hint at a massive shift. I unpack spatial scenes, shared experiences, and how these early tools are shaping tomorrow's web. We also look at how your living room might become a showroom, how eye tracking and intent will change UX, and why Gausian Splatting will play a major role in immersive AR. There’s plenty to critique — and even more to imagine. TL;DR: Apple’s VisionOS continues to push towards a spatial future. It’s not full AR yet, but the shift to immersive interfaces is undeniable. Spatial browsing, personalised retail, and shared digital experiences are just the beginning. Timestamps: 00:00 - VisionOS and Spatial Computing Overview 00:22 - Input and Control: Eye Tracking, Gestures, and Controllers 01:16 - Spatial Scenes and Apple’s 3D Browsing Effects 02:13 - Gaussian Splatting & Scanning with iPhone LiDAR 03:14 - Apple Personas, Overlays & Presenter UX 04:02 - Eye Tracking, Gesture Control & Intent 04:59 - Widgets as Portals & Spatial Weather Concepts 06:02 - Enterprise Use Cases & Shared Digital Experiences 06:48 - Safari’s Spatial Browsing and the Future of Retail UX 08:28 - Tailored, Transformative Websites 09:40 - Wrap-up: VisionOS Today and Tomorrow

The OS of the future won’t rely on mouse clicks and app folders — it will listen, respond, and build with you. In this Brainstream, I explore the next interface evolution: intelligent agents layered over your data, shortcut automation powered by natural language, and why Apple Mail still feels like it’s stuck in 2009. We dive into macOS and tvOS updates, talk frustrations with email, and uncover where Apple’s getting it right — and where it still falls short. TL;DR: Apple’s current updates feel like polishing old tools. We need conversational OS layers, shortcut agents, and a voice-powered rethink of creation — from building slides to managing email. 🎧 Listen to Layer[1]: → Website → Spotify → YouTube → Apple Podcasts Timestamps: 00:00 TVOS redesign & lyric sync wish list 01:36 First thoughts on MacOS: design tweaks and frustrations with Mail 02:25 Why Mail needs to evolve into an intelligent assistant 03:24 Tools used to improve communication (spreadsheet, Freeform, etc.) 04:44 Spotlight & app drawer comparisons 05:05 Clipboard history finally arrives 05:35 Vision for OS: executive assistant model 06:04 Shortcut “micro-prompt” ideas and automation possibilities 07:08 Email needs a rework: current apps aren’t cutting it 08:04 Journal Live Actions & iPhone mirroring feedback 08:58 Thoughts on intelligent shortcut actions & spotlight triggers 09:32 Outro

Apple’s WWDC just dropped a lot of new features—but did they miss the forest for the trees? In this episode, we dive into what was announced, what’s still missing, and where Apple’s headed when it comes to automation, personalised AI, and layered UI. From the unrealised promise of natural language Shortcuts to the potential of a true AI-powered workout coach, this Brainstream breaks it down. TL;DR: Shortcuts still aren't natural language, WatchOS introduces a coach concept, but it's far from personal, and Apple's layering between basic and complex apps still needs an overhaul. 👉 Listen to this Brainstream and discover what Apple could do next if they really embraced personalisation and agentic AI. 🎧 Listen to Layer[1] on Website, Spotify, YouTube, Apple Podcasts Timestamps: 00:00 Missed Stage Manager and Shortcut frustration 00:29 Siri Shortcut limitations & missed opportunities 01:20 Why natural language Shortcuts matter 02:09 The case for agentic Siri + LLM sidebar 03:10 WatchOS hands-free navigation 03:38 Smart layering between notes and pages 04:13 Workout Buddy: potential vs reality 05:14 Personalised coaching dream with AI 06:08 Tabata playlists, real-time motivation, and coaching tone 08:00 What could make the “Workout Buddy” truly smart 09:11 Beyond metrics: building a real AI coach

Apple’s WWDC didn’t just show off a new iOS—it hinted at an entirely new direction for how we’ll interact with our devices. From foundation models and voice transcription to a potential LayerOS-style rethink of app flow, this Brainstream dives deep into what’s here, what’s missing, and where Apple could go next. I reflect on past predictions, critique what Apple got right and wrong, and imagine a more fluid, AI-native interface that understands your workflows natively. TL;DR: Apple’s AI features are evolving, but the future is LayerOS—modular, intelligent, and seamless. Listen to Layer[1] on Website, Spotify, YouTube, Apple Podcasts Timestamps: 00:00 – Revisiting last year’s predictions 00:34 – Voice transcription still lacks accuracy 01:46 – Natural language shortcut building is still a dream 02:56 – LayerOS-style unified app flows 03:22 – Apple Silicon, Metal, and gaming push 04:00 – Foundation model access and the “small model” future 05:36 – Shortcuts, node-based automation, and infinite canvases 08:55 – AI-enhanced routing and live translation 09:36 – On-device transcription and APIs

Apple’s WWDC left subtle clues pointing to a major shift: the interface is no longer just flat and functional — it’s becoming physical, emotive, and alive. From liquid glass UI metaphors to camera-based visual intelligence, this Brainstream unpacks what Apple didn’t explicitly say — and what it all means for the future of interaction, accessibility, and space-aware design. Whether it’s how screenshots might evolve into something more dynamic, or how adaptive widgets in the sky point toward contextual computing, this is a brainstorm that blends critique with wonder. TL;DR: Apple’s visual choices hint at a paradigm shift toward physical, expressive, and spatial UIs. Liquid glass and screenshot-based interaction are more than design fluff — they’re the front line of new spatial thinking. 👇 Tap into this Brainstream and get ready to reimagine interface design. Listen to Layer[1] on 🌐 Website 🎧 Spotify 📺 YouTube 🍎 Apple Podcasts Timestamps: 00:00 – Opening thoughts & FaceTime presenter overlay gripes 01:30 – Liquid glass: physics, aesthetics & UI evolution 03:00 – Screenshots, refractivity & accessibility trade-offs 05:00 – Why liquid glass is more than a gimmick 06:00 – Visual intelligence and lock screen widgets 08:00 – Frustrations with MixEmoji and Apple’s image gen gap 09:00 – Final thoughts on vision and what’s missing

We’re two days post-WWDC, and my brain’s still buzzing. This isn’t a keynote recap — it’s a deep dive into why Apple’s “liquid glass” aesthetic signals something bigger. Think beyond the frosted UI — think spatial interfaces, contextual computing, and the death of the traditional app. What if the era of “learning the tool” is over, and we’re entering a time when tools learn us? I unpack Apple’s slow-burn philosophy, my long-held vision for a post-app world, and why these new design cues are shaping more than just your phone screen — they’re nudging the whole paradigm of computing forward. 👉 If you’re interested in how AI agents, spatial design, and user-centric computing collide — this one’s for you. TL;DR (Takeaways) Apple’s UI shift hints at a post-app world, not just visual polish. Liquid Glass = prepping for spatial computing, not skeuomorphic nostalgia. Traditional “tools” are giving way to agents that understand and work for us. This isn’t just design — it’s the architecture of a new computing mindset. Timestamps: 00:00 – WWDC: Expectations vs Reality 01:22 – TL;DR reaction to Apple’s approach 02:26 – Why we didn’t get flashy AI features 03:21 – Thoughts on Liquid Glass and accessibility issues 04:24 – The move toward spatial interface norms 06:03 – Rethinking screen limitations in the real world 06:44 – Introducing the post-app world concept 07:49 – Agents vs. tools: A paradigm shift 08:36 – The new master-slave dynamic in computing 09:28 – Liquid Glass: Sci-fi gimmick or visionary leap? 10:00 – Wrap-up & coming brainstorm Listen to Layer[1] → Website, Spotify, YouTube and Apple Podcasts

We’re reaching the limits of app-based creation—and there’s a new vision in town: Layer OS. What if your tools weren’t chosen before you started working, but emerged during the process, adapting as you moved? TL;DR Today’s apps are fragmented silos; LayerOS proposes a fluid, evolving interface. Tools should appear as you work—not force you to choose them upfront. Image and AI workflows are currently too separate; integration is overdue. Multimodal creation and predictive interfaces are the next UI frontier. LayerOS could function like an LLM OS—predicting interface needs instead of next words. In this brainstream, I go deep into the fractured nature of today’s apps and why we need a unified, predictive interface model—where your idea grows, and the interface evolves with it. Think of it like the operating system powered by AI prediction, surfacing tools layer by layer. I also touch on image generation, multimodal workspaces, and how we might finally break free from app silos. Ready to move beyond apps and into layers? Let’s build the future. 🎧 Listen to more brainstream of layer[1] now 👇 Website, Spotify, YouTube, Apple Podcasts Timestamps: 00:00 – Picking up where we left off 00:20 – Apple’s presenter mode frustration 01:02 – Why apps feel like the wrong tools 02:00 – Sketch vs Photoshop: same base, different goals 03:50 – The friction of switching tools 04:39 – The promise of LayerOS: tool-on-demand 05:33 – Why apps don’t speak well to each other 06:00 – AI nodes, canvases, and image editing gaps 07:03 – Why LayerOS belongs at the OS level 08:00 – My learning process: sharing the build live 08:34 – Multimodal work & future automation 09:10 – How layers could replace apps completely 09:35 – Why choosing the right app is broken 09:55 – The OS as an LLM that predicts interfaces #LayerOS #FutureOfUI #AugmentedReality #AIInterface #RealityOne #Brainstream #DesignThinking #CreativeTools #SpatialComputing #NoMoreApps

There’s something deeply wrong with how we “work” on computers. Why do we still sit in desks designed for typewriters? TL;DR - Today’s UI is still based on 1980s office metaphors - “Work” no longer happens at desks — ideas strike in hammocks, cars, and showers - LayerOS = infinite canvas, generative UI, conversational AI, asynchronous agents - Paradigm shift: from sandboxed apps to intelligent, context-aware layers - This isn’t about software—it’s about rethinking the foundation of computing In this raw brainstream, I unpack the limitations of today’s UI and introduce LayerOS — a reimagined operating system where context flows, interfaces evolve, and work is ambient, not static. From infinite canvases to asynchronous assistants and generative UIs, this isn’t a product pitch — it’s a shift in the mental model of computing itself. 🚀 If you’ve ever wanted your OS to think with you instead of slowing you down, this one’s for you. 👉 Listen in and tell me what you think — where is work heading in your world? Timestamps: 00:00 – The flaws in today’s UI paradigm 00:21 – Why the desktop metaphor no longer makes sense 00:48 – What is work now? Where is it happening? 01:40 – Computers should serve us — not vice versa 02:33 – Creativity doesn’t happen at the desk 03:44 – Asynchronous work and background processing 04:29 – Intro to LayerOS and its core ingredients 06:05 – Why these ideas keep recurring in Brainstreams 07:25 – Bringing theoretical frameworks into design 08:16 – The app model is outdated 09:33 – Documents, tools, and workflow fluidity 09:56 – Final thoughts on an iterative interface future 🌐 Listen to layer[1] on Website, Spotify, YouTube, Apple Podcasts #LayerOS #FutureOfWork #GenerativeUI #Brainstream #ConversationalAI #InfiniteCanvas #InterfaceDesign #AIUX #SpatialComputing