Show HN: AI reveals big companies secret strategies for business growth https://ift.tt/Xs5gKFI

Show HN: AI reveals big companies secret strategies for business growth EDOM.AI is the very first artificial Business-brain that allows you to Create , grow your business, start your business, and more. It gives you the secret strategies used by major companies like Nike, Apple, or Starbucks to inspire you from their success and lead your business to success. Walk on their success, learn from their mistakes, and make your dream come true. https://www.edom.ai/ April 9, 2024 at 11:44PM

Show HN: The fastest way to run Mixtral 8x7B on Apple Silicon Macs https://ift.tt/BEuvIQA

Show HN: The fastest way to run Mixtral 8x7B on Apple Silicon Macs I’d originally launched my app: Private LLM[1][2] on HN around 10 months ago, with a single RedPajama Chat 3B model. The app has come a long way since then. About a month ago, I added support for 4-bit OmniQuant quantized Mixtral 8x7B Instruct model, and it seems to outperform Q4 models at inference speed and Q8 models at text generation quality, while consuming only about 24GB of RAM[3] at 8k context length. The trick is: a) to use a better quantization algorithm and b) to use unquantized embeddings and the MoE gates (the overhead is quite small). Other notable features include many more downloadable models, support for App Intents (Siri, Apple Shortcuts), on-device grammar correction, summarization etc with macOS services and an iOS version (universal app), also with many smaller downloadable models and support for App Intents. There's a small community of users building and sharing LLM based shortcuts on the App's discord. Last week, I also shipped support for the bilingual Yi-34B Chat model, which consumes ~18GB of RAM. iOS users and users with low memory Macs can download the related Yi-6B Chat model. Unlike most popular offline LLM apps out there, this app uses mlc-llm for inference and not llama.cpp. Also, all models in the app are quantized with OmniQuant[4] quantization and not RTN quantization. [1]: https://privatellm.app/ [2]: https://ift.tt/UDthqFX [3]: https://www.youtube.com/watch?v=4AE8yXIWSAA [4]: https://ift.tt/M7GVovN April 8, 2024 at 09:37PM

Show HN: Dimity Jones in Puzzle Castle: An Electronic Escape Novel https://ift.tt/420GiPU

Show HN: Dimity Jones in Puzzle Castle: An Electronic Escape Novel _Dimity Jones In Puzzle Castle: An Electronic Escape Novel in Eighty-Nine Ciphertexts_ is a (mostly) fictional story, contained in a single text file, that requires the reader to solve puzzles as they go along, and to use each chapter's solution as a key to decipher the next. Think: escape room in the form of a novel. A computer, and rudimentary coding skills in a language of your choice, will be indispensable for performing the transformations -- and might help with the solving too! My wife, the author, passed away five years ago. This is not the last thing she wrote, but it is the most unusual, unapproachable, and personal of her major works. It is also, as the only novel of hers that I cannot breeze through in an afternoon (and despite my unflattering appearance in it), my favorite. Though _Dimity Jones_ was left unfinished, and perhaps abandoned, at the time of my wife's death, its elements were all there, on her hard disk, awaiting only a final compiling. My contribution to this text has therefore been little more than that of an occasional copyeditor (my wife was a meticulous speller and self-proofreader) and playtester. Before releasing this work more widely, I would love to have it test-driven by better coders and puzzlers than I. Any and all feedback is welcome, from positive to negative, from the sweeping to the picayune. Let me know what confuses or frustrates you -- and especially let me know if (where) you get stuck. Otherwise, there are no special instructions; it's all in the book. While _Dimity Jones_ is still in its debugging/proofreading phase, please refrain from sharing it or putting it any (other) public place. (Christine would have been horrified to see her work thus published before it was letter-perfect; but I have exhausted my pool of friends and colleagues both able and willing to tinker with it. This seems like the ideal community of potential testers.) Thanking you in advance. I hope you enjoy! https://ift.tt/FRYkBdl April 9, 2024 at 12:17AM

Show HN: Neco – Coroutine Library for C https://ift.tt/UFj8kwV

Show HN: Neco – Coroutine Library for C https://ift.tt/psi0B6m April 8, 2024 at 11:07PM

Show HN: AutoMQ - A Cost-Effective Kafka Distro That Can Autoscale in Seconds https://ift.tt/4A5UPpZ

Show HN: AutoMQ - A Cost-Effective Kafka Distro That Can Autoscale in Seconds https://ift.tt/RrfIyAz April 8, 2024 at 09:35AM

Show HN: HomeStage – Instant virtual furnishing with one click https://ift.tt/3rAvwJN

Show HN: HomeStage – Instant virtual furnishing with one click https://homestage.app April 8, 2024 at 02:40AM

Show HN: Flash Notes – Flashcards for Your Notes, LLM, iOS/macOS Sync https://ift.tt/SbZ83TK

Show HN: Flash Notes – Flashcards for Your Notes, LLM, iOS/macOS Sync The app started as my wishful thinking that flashcards should really be derived from notes. I've been constantly writing things down and wishing to remember them. However, I never could convince myself to populate a flashcard app with them. I really tried (Anki, Supermemo), but I guess regular form filling is not for me. So I've started experimenting with flashcards derived from structured notes. Writing the 1st MVP was fast, but productionising it was way harder. Content synchronisation when the user can work from tube/plane and use multiple devices and content is text is… not trivial. So I had to learn about OT (Operational Transformation) and CRDT (Conflict-Free Replicated Data Type), and even implemented a few iterations of CRDT in Swift. This was intellectually rewarding, but the app was not progressing. Also, when you have both app data model and CRDT in your head, you start to over-optimize - you are leaking abstractions. Thankfully, the CRDT market nowadays is pretty mature; Automerge is production-ready, and automerge-swift comes with a nice abstraction. I strongly believe offline-first apps are the future/now. ChatGPT happened, and it felt like a perfect match for the app, as it's already text-focused. First, it was just to provide prompts for the cards, but when you turn the problem around, you realise that LLM is great for predicting other flashcards in the context of your note. So instead of downloading a premade flashcard deck, you start a new note, give it a title, and click generate. I still find it weird to watch but also mesmerising. Other features that I think are valuable: App data sits within your iCloud account until you use Generative AI (LLM). Hopefully, we will get an API from Apple soon. The Spaced Repetition that I've implemented is not really spaced. I wanted the app to adapt to the user. So it's focusing on sorting the card deck based on your recall and lets you practise as much as you want. I found this approach to work way better for me. Oh, it's multilingual with text-to-speech. Here we are; the 1st production-ready "MVP" is live. I'd love to hear your feedback. https://ift.tt/MUsyXgP April 7, 2024 at 11:24PM