Show HN: Bluesky Hacker News Bot https://bit.ly/3w41BO1

Show HN: Bluesky Hacker News Bot Hello there! After Bluesky opened its doors to everyone, I jumped straight into the API to build something. Here is a bot that posts top stories from HN. https://bit.ly/42D42Dp February 7, 2024 at 11:00AM

Show HN: DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors https://bit.ly/3SyWnRM

Show HN: DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors Hello HN! We have released a major update of our image-to-video diffusion model, DynamiCrafter, with better dynamic, higher resolution, and stronger coherence. DynamiCrafter can animate open-domain still images based on text prompt by leveraging the pre-trained video diffusion priors. Please check our project page and paper for more information. We will continue to improve the model's performance. Comparisons with Stable Video Diffusion and PikaLabs can be found at https://www.youtube.com/watch?v=0NfmIsNAg-g Online demo: https://bit.ly/3uzEnie Our project page: https://bit.ly/3OBc7Tc Arxiv link: https://bit.ly/4bvjxRI https://bit.ly/485S7iI February 7, 2024 at 08:12AM

Show HN: I made a local wrapper for Automatic 1111 https://bit.ly/3SrGZa5

Show HN: I made a local wrapper for Automatic 1111 I made an open-source Python library for the Stable Diffusion Web UI. It's a direct alternative to Huggingface Diffusers except it has more features + runs the same scripts as A1111 so the results are replicable. Please give it a star on Github! https://bit.ly/3SxSaOk https://bit.ly/3SxSaOk February 7, 2024 at 06:55AM

Show HN: Kirby-like platformer game made in TypeScript https://bit.ly/49sHasB

Show HN: Kirby-like platformer game made in TypeScript https://bit.ly/49fCVjY February 5, 2024 at 10:45PM

Show HN: How we got fine-tuning Mistral-7B to not suck https://bit.ly/3SPTopL

Show HN: How we got fine-tuning Mistral-7B to not suck https://bit.ly/42vSmCl February 6, 2024 at 08:12AM

Show HN: CPU Prices on eBay https://bit.ly/49lQXR9

Show HN: CPU Prices on eBay Tech stack: Go + templ + htmx There are some rough edges but this combo is quite refreshing after React. The best thing is that I could omit npm from my stack. Having just a monolith (Go) server greatly simplifies things if you're an indie dev. https://bit.ly/49p5cVm February 5, 2024 at 04:43PM

Show HN: An opinionated TS package build toolchain with typed configuration https://bit.ly/3SIZsAi

Show HN: An opinionated TS package build toolchain with typed configuration https://bit.ly/3SK3TdX February 5, 2024 at 02:47AM

Show HN: ReadToMe (iOS) turns paper books into audio https://bit.ly/492kzDf

Show HN: ReadToMe (iOS) turns paper books into audio I'm launching something that started as a side project publicly today: ReadToMe, which is an iPhone app that turns paper books and other printed text into audio. Originally this was a Christmas present for my fiancée, who loves books but has an eye problem that makes it hard for her to read more than a few pages at a time. She mostly listens to audiobooks while following along with the paper book, but some books aren't available in audiobook or even e-book form, and all of the existing apps we tried were surprisingly bad at scanning paper books into audio — they make lots of mistakes, include footnotes and page numbers, etc., in a way that really degrades the experience. Being an AI-oriented engineer by training, I had a crack at solving the problem myself, and was pleasantly surprised at how well the proof of concept worked. I then had some time free while shutting down my previous company (Mezli, YC W21), during which I polished up the app to the point you see it at now. The way it works: On the front end, it's a SwiftUI app (mostly written by ChatGPT!) that consists mostly of a document scanner (VNDocumentCameraViewController) and a custom-built audio player. The back end is more complex — book photos are first sent to an OCR API, then some custom code I wrote does a first pass at stitching together and correcting the results. Then, the corrected OCR results are sent to GPT-3.5-turbo for further post-processing and re-stitching together, and finally to a text-to-speech API for conversion to audio. The hardest part of this process was actually getting the GPT calls right — I ended up writing a custom LLM eval framework for making sure the LLM wasn't making edits relative to the true text of the book. A few issues remain, which I'll work on fixing if the app gets a significant amount of traction, including: 1) It can take multiple minutes to get audio back from a scan, especially if it's on the longer side (10+ pages). I'll be able to bring this down by spinning up dedicated servers for the OCR and TTS back-end. 2) The LLM sometimes does TOO good of a job at correcting "mistakes" in book text. This issue crops up particularly often when an author deliberately uses improper grammar, e.g. in dialogue. The app is priced at $9.99/month for up to 250 pages/month right now, which I estimate will just about cover the costs of API calls. I'll be bringing the price point down as the pricing of the required AI APIs comes down. There's also a 3-day free trial if you want to try it out. If you do find this useful, or know somebody who might, I'd appreciate you giving it a try or letting them know! And please let me know if you have any feedback, including issues or feature requests. https://bit.ly/484Yd2A February 5, 2024 at 12:56AM

Show HN: Letlang, written in Rust, targeting Rust, now has a specification https://bit.ly/48joCKt

Show HN: Letlang, written in Rust, targeting Rust, now has a specification https://bit.ly/3ubLjSR February 4, 2024 at 02:17PM

Show HN: Aidely is AI powered thread; AI and Humans cooperation https://bit.ly/42oVH6g

Show HN: Aidely is AI powered thread; AI and Humans cooperation Discover the future of community engagement with our iPhone app. Seamlessly blend human creativity with AI prowess as users collaborate with ChatGPT, Bard, and Llama to spark captivating threads and discussions. Join us in shaping the next frontier of content creation. https://bit.ly/42sZlfx February 4, 2024 at 03:48PM

Show HN: USD 0.99/TB/month cloud storage https://bit.ly/3uhzxGv

Show HN: USD 0.99/TB/month cloud storage https://bit.ly/3SKxcx6 February 4, 2024 at 03:16PM

Show HN: Unofficial Google Lens OCR API https://bit.ly/3OxpO5H

Show HN: Unofficial Google Lens OCR API Default OCR in ShareX is pretty bad, so I reverse-engineered Lens API and made a library to call unofficial Lens API and made a script for ShareX to OCR the captured region. URL points to library I've made, there's a tutorial for ShareX in separate file: https://bit.ly/3I5OZZH... https://bit.ly/3I5P0Nf February 4, 2024 at 01:08PM

Show HN: A Python PDF Form Library https://bit.ly/3uk7bLC

Show HN: A Python PDF Form Library Hi HN! I have a project that I have been working on for three years that I’d love to show you today called PyPDForm ( https://bit.ly/3HJylyE ). It is a Python library that specializes in processing PDF forms, with the most outstanding feature being programmatically filling a PDF form by simply feeding a Python dictionary. I used to work at a startup company with Python as our backend stack. We were constantly given paper documents by our clients that we needed to generate into PDFs. We were doing it using reportlab scripts and I quickly found the process tedious and time consuming for more complex PDFs. This is where the idea of this project came from. Instead of writing lengthy and unmaintainable reportlab scripts to generate PDFs, you can just turn any paper document into a PDF form template and PyPDFForm can fill it easily. On top of the GitHub repo, here are some additional resources for this project: PyPi: https://bit.ly/48X4te4 Docs: https://bit.ly/49nVTon A public speak I did about this project: https://www.youtube.com/watch?v=8t1RdAKwr9w I hope you guys find the library helpful for your own PDF generation workflow. Feel free to try it, test it, leave comments or suggestions, and open issues. And of course if you are willing, kindly give me a star on GitHub. https://bit.ly/3HJylyE February 4, 2024 at 02:25AM

Show HN: Oh My ZSH Aliases https://bit.ly/3SqbDAH

Show HN: Oh My ZSH Aliases https://bit.ly/3SKjw4b February 3, 2024 at 04:45AM

Show HN: BP.AdventureFramework, a framework for writing text adventures in C# https://bit.ly/3HKUBIo

Show HN: BP.AdventureFramework, a framework for writing text adventures in C# BP.AdventureFramework is a framework written in C# targeting .Net Standard 2.0. It provides all of the core classes and logic required to write rich text adventures and interactive fiction. Games run in a terminal window - ANSI support is not essential but is recommended however the NO_COLOR environment variable can be used to suppress colour. https://bit.ly/3HIwqdN February 3, 2024 at 01:06AM

Show HN: Brainbase (YC W24) – ship enterprise grade AI features in minutes https://bit.ly/3SK1Tmc

Show HN: Brainbase (YC W24) – ship enterprise grade AI features in minutes https://bit.ly/3SIqFTt February 3, 2024 at 05:25AM

Show HN: HN stories categorized by topics of interest https://bit.ly/3UlNz4s

Show HN: HN stories categorized by topics of interest Hi HN, TL;DR: I made a website that takes all the top stories on HN and categorizes them into one of ten topics of interest using LangChain and GPT-4. I've always liked the idea of getting a personal mix of news tailored to my interests. Hacker News is pretty close to that ideal, which is reflected in the time I spend on here every day. It's a great mix, but playing with LangChain, I got the idea for a weekend project. Roughly speaking most posts on HN fall into one of these categories: * Programming, Software & Computer Science * AI, Data Science & Analytics * Business & Entrepreneurship * Science & Research * Cybersecurity & Digital Safety * Design, User Experience & Creativity * Finance & Economics in Tech * Work Culture & Career Development * Media, Content & Communication * General & Diverse Interests Using langchain with GPT-4 Turbo (JSON mode), I sort every top submission into one of the above. Costs for using the API are currently at 15$ a month, with few optimizations. For ease of use I also added the possibility to consume the news topics via a responsive webpage, RSS and email digest (daily,weekly,monthly). https://bit.ly/3u8mKWU February 2, 2024 at 11:00PM

Show HN: Write Documentation Easily https://bit.ly/481EbpT

Show HN: Write Documentation Easily Docs+ is a low-code easy way for developers to share Onboarding documents, API documentation, and much more in an easy way. Create sections and sub-sections, create unlimited pages, and share via a single link to anyone! Docs+ has a huge roadmap ahead and We're happy to hear feedback and make the product better!! https://bit.ly/3HHGOCz February 2, 2024 at 11:56AM

Show HN: Automate Variable Selection for Research on Big Datasets (Open-Source) https://bit.ly/4bpkZoL

Show HN: Automate Variable Selection for Research on Big Datasets (Open-Source) https://bit.ly/4bpl1gn February 1, 2024 at 09:04PM

Show HN: filippo.io/mlkem768 – Post-Quantum Cryptography for the Go Ecosystem https://bit.ly/48Wp7uY

Show HN: filippo.io/mlkem768 – Post-Quantum Cryptography for the Go Ecosystem https://bit.ly/42kVvVo February 1, 2024 at 12:10PM