Introducing MLX-Swift-TS An SDK for running time series foundation... models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.show more

Today I'm launching a very early release of MLX... Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.show more

Pure MLX of UMAP, t-SNE, PaCMAP, TriMap, DREAMS, and... CNE for Apple Silicon. Beyond the algorithms, I also built a circle-splatting renderer in MLX - scatter-add alpha blending on Metal, piped to H264 hardware encoding. So 70K points, 784 dimensions, from raw data to rendered video < 5s on M3 Ultra. pip install mlx-vis Paper: Code:show more

Qwen 3.5 0.8B, Gated DeltaNet attention is running on... Apple Neural Engine ~56 t/s in LUT6 quantization with some room for optimization left. It is CoreML, Swift and IOSurface on M4Pro. It will slow down as we increase context, but not by much. I think Private API opens the way to integrate ANE with GPU/MLX and possibly some MoE.show more

Today, we're shipping MLX support for TADA, our open-source... text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.show more

I'm not an engineer, but I rebuilt Savee —... the app a million designers use Friday, 5pm. I asked Claude how much work it would take to rebuild our iOS app fully native. It had been sitting on our someday list for years, waiting for a team we didn't have. I stopped waiting and built it myself — a designer with Claude Code, one feature at a time. Claude wrote the Swift; I answered with the feedback designers give: two points left, lighter tint, that corner radius is wrong. Another round. And another. 33 days from the first prompt to live on the App Store. 1,078 prompts. Three releases in the first week. Something changed for designers. The distance between an idea and shipping used to be a team, a budget, and a year. Now it's a conversation. Savee 3.0 is out. It's the app I always wanted us to have 🚀show more

made something I wanted for a while: a high... performance custom tab/splits library in swift for native Mac apps. with support for drag/drop, CoreAnimation accelerated transitions, and more. spent a lot of time on the polish of this thing to feel snappy, but fun.show more

“They asked if I would mind if Taylor Swift... did this thing, and I said, ‘No one’s ever going to say no to her,’ we had an hour, maybe an hour and a half [to rehearse]. She knew the song. There wasn’t anything to do, I said, ‘Do you want to do it in another key?’ But she said no.” — Randy Newman spoke to Variety on his duet with Taylor Swift for “You’ve Got A Friend In Me” at the ‘Toy Story 5’ premiere. 🥹show more

Late night gym and swim. Fit. Healthy. Confident. Steadfast.... My swift responses to Irelands issues and needs has been a direct rocket each time. You have fully agreed with all my points. No one on this ballot has what I have, nor the ability to do what I do, for the people and land of Ireland, of which I hold so dear! McGregor as Irelands President is A LOCK! 🔒show more

Last year, almost to the day, Kayla Nicole went... on Angel Reese podcast and talked about getting dumped by an NBA player and dressing up as the girl she got dumped for for Halloween. That was Teyana Taylor that she was shading. A week ago, Taylor Swift went on Jimmy Fallon and said the last movie she watched was the one starring the one and only, Teyana Taylor lol. She praised all the actors. Taylor swift is a GD mastermind and I love it. I have seen NO ONE catch this…. If it starts going viral, remember where you heard it first. #TaylorSwift #Swiftieshow more

Vercel's AI SDK 7 ships HarnessAgent, an API for... running established agent harnesses like Claude Code, Codex, and Pi. Write the agent once, then use whatever harness is best for your use case. Try building a creative production agent with Pi using the Vercel AI SDK: one image model makes the hero shot, then an E2B sandbox runs Python to cut the backdrop, render every specified size, overlay copy, audit WCAG contrast and palette share, and serve the finished ad set on a live URL. Full example in the cookbook:show more

I love this, so I made a minimalist version... for myself. When an agent is running in Codex, Pac-Man is eating 👾 and becomes all big and green 🤢 when the agent is done, so I know it's time to prompt again. On hover, the notch expands to show the list of running and completed threads. Edward Luo came up with a banger, and I think the Codex team should consider adding this natively because it's really nice 🤗show more

GPT-5.5 is MUCH more reliable on longer running tasks... - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.show more

As for my summit dreams, they will have to... wait There are no guarantees in mountaineering - I made the call at the South Col with respect to the Everest summit, that I was not in a sufficiently fit state to make an attempt, so I did not head off for the summit push. Given the dangers involved, I could not in good conscious make an attempt on the summit and potentially put myself and my Sherpa in peril. The mountain takes a swift toll on people who fail to leave sufficient energy in reserve for the descent. I tried to remain positive and head for the Lhotse summit on 24 May 2023 - the mind was willing but my body was not on the same page unfortunately, so I made a retreat for the safety of camp 2 2/3show more

HOLY MOLY running a 35B model locally on a... MacBook shouldn’t be THIS FAST 🤯 Spent my weekend in atomic.chat testing Qwen 35B vs. Qwen 27B on my local machine. I had them generate a fully animated HTML/Canvas car mini-game (demo below), ... and both models breezed through the physics and parallax scrolling without a hitch! The secret sauce here is the Atomic Chat app. Because it's perfectly optimized for Mac and uses Google's new TurboQuant under the hood, you can run heavy open-source models flawlessly while keeping top-tier output quality 👊 Other perks: → ZERO setup required → Access 1,000+ models completely free → 100% offline and private → Zero API limits ... and MUCH more! I dropped the prompt I used in the 🧵↓ Spin it up locally and let me know what you get!show more

Thalians, our girl needs us now more than ever🙏🏼Remember... this will be the last time YOU & I VOTE for her, let’s triple our efforts so when Sunday comes, we can pat ourselves on the back & say we did that!🥹 • It’s always 10 numbers per device • ⁠Change to desktop site after voting to get extra 100votes. 1number =200votes • Once you’ve used 10 numbers on one device, DO NOT vote again on that device • If you still want to vote, switch to a different device and use new numbers 🔗: #ThandekaTshabalala #BBMzansi #BBMzansiS6show more

We are bootstrapping our app studio to $1M/mo It’s... based around screen time apps. We have prayer lock with 13k reviews ranking top #100 on the AppStore Now we are building step lock our 2nd app and the first goal is to scale it. to $10k/mo, In public It combines health kit + screen time api To block your apps until you get your steps in. We used Rork plans feature, and it literally gave us the whole setup for the app, Then it built the app for us and one shorted the api integrations In a 2 days we had the app submitted to the AppStore The app is currently in review. Apple has rejected it 7 times For the dumbest reasons. But it’s looking like this time it will get approved. Will be posting updates on thisshow more

I wish to sincerely apologise to the residents of... Lakeside and its environs for the inconvenience caused. There have been multiple faults on cables connected to the feeder, one of which was located in the middle of a road. As a result, excavation works took some time to safely access and isolate the fault. Repair works are currently underway. Our technical team remains on site and will continue working until power supply is fully restored.show more

Cancelled ChatGPT -> Built JARVIS -> Pays $0 ->... it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.show more

" A mattress. Well Maybe for some individuals. "... This is something based on a comic I made with Ai in the past. I had the comic animated with Atlabs AI The video pretty much says what everything is about. I honestly like silly comics like this. I really should make more and have them as videos as well. That's another things for a long list of things I need done... Also I plan on running more tests with Omniflash in the future especially when Seedance models may not do things a certain way or have things looking a certain way. Also if anybody is planning on using Atlabs for anything I plan on making a video next month on how I use certain video models and which I typically use. This is specifically on how I use certain models for certain things. Not MG. I plan on having it in a tutorial section. I have hopes this will provide people that use any video models with some needed help when choosing what they should get started with because a Sora video model is no longer an option, which was very integral involving how I would use video models in general. Anyway I have an atlabs link below. If you make an account or have one already I hope what I plan on making next month and showing you, helps a lot. This was made with AtlabsAi. This was all done with Ai. #furrycomedyvideo #furryvideo #aianimation #aifurryshow more