Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

This is so cool - fully on-device semantic search. Type "glass" and get clips with liquid glass. No manual tags needed. Runs an on-board MiniLM, vision ML, OCR and RRF fusion to blend signals to output. That's a mouthful, but means very speedy, hands-off and local on your Mac

Tobias Renström

13,458 subscribers

20,389 Aufrufe • vor 1 Monat •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We are introducing a whole new refreshed Craft. It feels new, yet familiar, with Apple’s Liquid Glass, on-device AI, a sharper iPad experience, and thoughtful updates to Tasks, Collections, and Tags.

We are introducing a whole new refreshed Craft. It feels new, yet familiar, with Apple’s Liquid Glass, on-device AI, a sharper iPad experience, and thoughtful updates to Tasks, Collections, and Tags.

Craft.do

32,723 Aufrufe • vor 11 Monaten

I see Liquid Glass everywhere but the problem is everyone’s created a sphere and that’s it. I prefer to create systems. I’ve Vibecoded the full-fledged cpu based universal Liquid Glass design system that works on every browser and device , getting closer and closer to the official iOS 26 one. Still working in progress before a full release.

I see Liquid Glass everywhere but the problem is everyone’s created a sphere and that’s it. I prefer to create systems. I’ve Vibecoded the full-fledged cpu based universal Liquid Glass design system that works on every browser and device , getting closer and closer to the official iOS 26 one. Still working in progress before a full release.

Tykra

41,704 Aufrufe • vor 3 Monaten

I designed the levels so anything concrete is climbable, but metal and glass are not. So you gotta figure out how to get to the destination on your own it's very freeform

I designed the levels so anything concrete is climbable, but metal and glass are not. So you gotta figure out how to get to the destination on your own it's very freeform

Brian - No Walls In Heaven

391,750 Aufrufe • vor 4 Monaten

Meet Liquid ShieldFlow. An on-device privacy layer powered by a device-native Liquid Foundation Model, Liquid ShieldFlow redacts sensitive data before it ever leaves your machine. No GPU needed and light on memory. It runs on almost any PC, locally, in real time. ShieldFlow was featured yesterday at Microsoft Build for Foundry Local. It also ran live on AMD laptops at 𝐂𝐎𝐌𝐏𝐔𝐓𝐄𝐗 𝐓𝐀𝐈𝐏𝐄𝐈. Request your early access here to ShieldFlow here:

Meet Liquid ShieldFlow. An on-device privacy layer powered by a device-native Liquid Foundation Model, Liquid ShieldFlow redacts sensitive data before it ever leaves your machine. No GPU needed and light on memory. It runs on almost any PC, locally, in real time. ShieldFlow was featured yesterday at Microsoft Build for Foundry Local. It also ran live on AMD laptops at 𝐂𝐎𝐌𝐏𝐔𝐓𝐄𝐗 𝐓𝐀𝐈𝐏𝐄𝐈. Request your early access here to ShieldFlow here:

Liquid AI

20,864 Aufrufe • vor 2 Monaten

Linux phone navigation is coming together. The future is your phone being fully agentic and being able to modify itself and write software for you on the fly. Ram is very limited on this device but I will see how a fully local model will perform, something sub 1.5B.

Linux phone navigation is coming together. The future is your phone being fully agentic and being able to modify itself and write software for you on the fly. Ram is very limited on this device but I will see how a fully local model will perform, something sub 1.5B.

vlad

127,874 Aufrufe • vor 1 Monat

This is how you build the next generation of AI applications. You need an idea, a good model architecture, and a great harness. That's what MUZIM did. It's an app that runs local multimodal and vision models offline to parse and index your images, videos, and documents frame by frame. • Super fast on-device processing • On-device video & image understanding • You can also bring your API keys for heavy reasoning • Your data stays where it is / nothing goes to the cloud You can do a couple of things with this: 1. Vibe searching for whatever you remember in photos or raw video clips. The app will jump straight to the exact frame and timestamp of the video. This is search as it should be. 2. Use local-running agents to perform tasks on your files. I show a couple of examples in my video. You can check it out here: Thanks to the MUZIM by OpenSoul team for showing me the tool and partnering with me on this post.

This is how you build the next generation of AI applications. You need an idea, a good model architecture, and a great harness. That's what MUZIM did. It's an app that runs local multimodal and vision models offline to parse and index your images, videos, and documents frame by frame. • Super fast on-device processing • On-device video & image understanding • You can also bring your API keys for heavy reasoning • Your data stays where it is / nothing goes to the cloud You can do a couple of things with this: 1. Vibe searching for whatever you remember in photos or raw video clips. The app will jump straight to the exact frame and timestamp of the video. This is search as it should be. 2. Use local-running agents to perform tasks on your files. I show a couple of examples in my video. You can check it out here: Thanks to the MUZIM by OpenSoul team for showing me the tool and partnering with me on this post.

Santiago

64,932 Aufrufe • vor 4 Tagen

BOTH SIDES OF THE GLASS IS OUT TODAY!! We poured our hearts and souls into this book (pun intended), and we can’t wait for you all to get your hands on it. Available NOW! 🥂

BOTH SIDES OF THE GLASS IS OUT TODAY!! We poured our hearts and souls into this book (pun intended), and we can’t wait for you all to get your hands on it. Available NOW! 🥂

Neil Patrick Harris

87,555 Aufrufe • vor 10 Monaten

"Come on.. you can't be that dumb", Kerry Roberts proclaims as she attempts to explain how silly it sounds for the cocktail glass to have been found by John O'Keefe. You're right Kerry, it's ridiculous. It's ridiculous to think the same hand that supposedly received a direct hit with an SUV (that had received no injuries from this very hit) somehow managed to grasp this cocktail glass as it broke. This same body then did a spin, with the broken glass in hand, got launched 10 feet, and said glass landed right next to the body. Or does it make more sense that a body holding a cocktail glass received a strike on the back of the head and the glass broke as the hand released the grip on the glass as the body fell. This wouldn't be the first murder where evidence was placed to look staged. Riddle me this Kerry... Is this why, til this very day, the entirety of the glass has never been found? Is this why the glass on the bumper did not match? Or the majority of the glass at the scene did not match? Where's the rest of the glass, Kerry?

"Come on.. you can't be that dumb", Kerry Roberts proclaims as she attempts to explain how silly it sounds for the cocktail glass to have been found by John O'Keefe. You're right Kerry, it's ridiculous. It's ridiculous to think the same hand that supposedly received a direct hit with an SUV (that had received no injuries from this very hit) somehow managed to grasp this cocktail glass as it broke. This same body then did a spin, with the broken glass in hand, got launched 10 feet, and said glass landed right next to the body. Or does it make more sense that a body holding a cocktail glass received a strike on the back of the head and the glass broke as the hand released the grip on the glass as the body fell. This wouldn't be the first murder where evidence was placed to look staged. Riddle me this Kerry... Is this why, til this very day, the entirety of the glass has never been found? Is this why the glass on the bumper did not match? Or the majority of the glass at the scene did not match? Where's the rest of the glass, Kerry?

BoozeyBeauty

39,510 Aufrufe • vor 8 Monaten

There’s something about a real glass of bourbon and some Fleetwood Mac. It may be for boomers, but it's also really nice. It’s Friday, so Josh Holmes, Comfortably Smug, Michael Duncan and John Ashbrook are here to kick off your weekend! Full show on YouTube now.

There’s something about a real glass of bourbon and some Fleetwood Mac. It may be for boomers, but it's also really nice. It’s Friday, so Josh Holmes, Comfortably Smug, Michael Duncan and John Ashbrook are here to kick off your weekend! Full show on YouTube now.

Ruthless Podcast

16,667 Aufrufe • vor 1 Jahr

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.

QVAC

23,973,950 Aufrufe • vor 1 Monat

23yo Mo Gueye is a menace… 6’11 with a 7’3.5 wingspan but moves like a wing. Extremely defensively versatile. Offenses feel squeezed by his length and motor. Also mauls the glass. Type of guy you love to have on your team and hate to play against.

23yo Mo Gueye is a menace… 6’11 with a 7’3.5 wingspan but moves like a wing. Extremely defensively versatile. Offenses feel squeezed by his length and motor. Also mauls the glass. Type of guy you love to have on your team and hate to play against.

Basketball University

59,183 Aufrufe • vor 7 Tagen

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 Aufrufe • vor 1 Monat

Tom Hanks reveals he insisted on recreating Fred Rogers' real morning routine on set. But the crew could only offer a prop glass of "red liquid" for the scene. "I asked Joanne Rogers, 'What did Fred drink in the morning?' and Joanne said, 'No, he drank hot cranberry juice!'" "I went to Marielle Heller and I says, 'Is there any way we can get this?'" "She says, 'The most we're going to be able to do is have a glass of red liquid sitting on the counter while you're talking on the phone.'" "I said, 'Good enough for me, as long as we can get that.'"

Tom Hanks reveals he insisted on recreating Fred Rogers' real morning routine on set. But the crew could only offer a prop glass of "red liquid" for the scene. "I asked Joanne Rogers, 'What did Fred drink in the morning?' and Joanne said, 'No, he drank hot cranberry juice!'" "I went to Marielle Heller and I says, 'Is there any way we can get this?'" "She says, 'The most we're going to be able to do is have a glass of red liquid sitting on the counter while you're talking on the phone.'" "I said, 'Good enough for me, as long as we can get that.'"

thelotachi 🔲⛓️

424,844 Aufrufe • vor 1 Monat

Elon Musk says he is not working on making a phone, and shares his thoughts on the future of telecommunications: “I am not working on a phone. A phone will really be an edge node for Al inference, for Al video inference. With, you know, with some radios to obviously connect to, but essentially you'll. have Al on the server-side, community communicating to an Al on your device. I think that there won't be operating systems. There won't be apps in the future. There will be operating systems or apps; it'll just be you've got a device that is there for the screen and audio, and for, and, and to put as much Al on the on on the device as possible, so as to minimize the amount of bandwidth that's needed between your edge node device, formally known as a phone, and the servers.”

Elon Musk says he is not working on making a phone, and shares his thoughts on the future of telecommunications: “I am not working on a phone. A phone will really be an edge node for Al inference, for Al video inference. With, you know, with some radios to obviously connect to, but essentially you'll. have Al on the server-side, community communicating to an Al on your device. I think that there won't be operating systems. There won't be apps in the future. There will be operating systems or apps; it'll just be you've got a device that is there for the screen and audio, and for, and, and to put as much Al on the on on the device as possible, so as to minimize the amount of bandwidth that's needed between your edge node device, formally known as a phone, and the servers.”

Nic Cruz Patane

17,796 Aufrufe • vor 9 Monaten

Obsidian Properties. A simple way to add structured data to your notes: dates, tags, checkboxes, lists, even links. You can also search notes by property and value. ✨ Now available to all with Obsidian 1.4. As always, your data is stored durably and privately on your device.

Obsidian Properties. A simple way to add structured data to your notes: dates, tags, checkboxes, lists, even links. You can also search notes by property and value. ✨ Now available to all with Obsidian 1.4. As always, your data is stored durably and privately on your device.

Obsidian

233,794 Aufrufe • vor 3 Jahren

Thrilled to unveil what we've been cooking the last few weeks: the Gravity AI assistant. Local, free, owned by you. Now available for free on macOS -> GravityAI 🌠 Gravity ensures absolute privacy by keeping all conversations on your device. No compromises, your data is exclusively yours. Plus, with LLaVa and OCR, Gravity gains vision – just snap a screenshot, and it's ready to chat about anything on your screen. Everything has been built to optimize the power of Apple silicon: I used Mistral AI as a base LLM and a in-app instance of ollama. It is insanely fast. Gravity will continue to evolve from here. For example, we're working on speech recognition and speaker diarization to passively learn from your meetings and messages in the background, no integrations needed. Incredibly proud of our journey so far and a big shoutout to my co-founder Tye Daniel for grinding to make this happen (we were up till 4am making sure this ships today) We're hiring folks with talent and passion, and we welcome you to join us on this exciting journey!

Thrilled to unveil what we've been cooking the last few weeks: the Gravity AI assistant. Local, free, owned by you. Now available for free on macOS -> GravityAI 🌠 Gravity ensures absolute privacy by keeping all conversations on your device. No compromises, your data is exclusively yours. Plus, with LLaVa and OCR, Gravity gains vision – just snap a screenshot, and it's ready to chat about anything on your screen. Everything has been built to optimize the power of Apple silicon: I used Mistral AI as a base LLM and a in-app instance of ollama. It is insanely fast. Gravity will continue to evolve from here. For example, we're working on speech recognition and speaker diarization to passively learn from your meetings and messages in the background, no integrations needed. Incredibly proud of our journey so far and a big shoutout to my co-founder Tye Daniel for grinding to make this happen (we were up till 4am making sure this ships today) We're hiring folks with talent and passion, and we welcome you to join us on this exciting journey!

Sulaiman Khan Ghori

71,430 Aufrufe • vor 2 Jahren

Raise a glass to VA-11 Hall-A's iconic bartender protagonist, working class hero, and birthday girl, Jill Stingray! VA-11 Hall-A is on sale for 33% off on Steam, so hop on and decorate her apartment with something she'll like. Join us on TikTok 👇

Raise a glass to VA-11 Hall-A's iconic bartender protagonist, working class hero, and birthday girl, Jill Stingray! VA-11 Hall-A is on sale for 33% off on Steam, so hop on and decorate her apartment with something she'll like. Join us on TikTok 👇

Ysbryd Games | LOVE ETERNAL OUT NOW!

25,124 Aufrufe • vor 1 Jahr

“you think the world is full of women dying to ride on your white horse, but those cinderella stories aren't popular anymore. in the real world, the world is filled with women who work hard and succeed on their own. so take your glass shoes, and feed them to dogs.” -choi aera

“you think the world is full of women dying to ride on your white horse, but those cinderella stories aren't popular anymore. in the real world, the world is filled with women who work hard and succeed on their own. so take your glass shoes, and feed them to dogs.” -choi aera

moon ˚.⋆☽˚.⭒

752,776 Aufrufe • vor 5 Monaten

In case you missed it, Patch 7 is coming to PC next week! With so many changes and new features arriving in this patch, it’ll take a little longer to get these to you on console and Mac - but don’t worry, you’ll be murdering your enemies and installing mods in no time.

In case you missed it, Patch 7 is coming to PC next week! With so many changes and new features arriving in this patch, it’ll take a little longer to get these to you on console and Mac - but don’t worry, you’ll be murdering your enemies and installing mods in no time.

Baldur's Gate 3

616,717 Aufrufe • vor 2 Jahren