The best Hacker News stories from Show from the past week
Latest posts:
Show HN: Customizable, embeddable Chat GPT based on your own documents
Hi Hacker News!<p>My name is Bea, I built a site called Libraria that uses GPT to do a few things<p>1. Let you spin up multiple assistants based on your own documents. You can make it public, private, or protected. It has its own subdomain and landing page.
2. Respond in full markdown always, so it can output images, links, code, and more
3. Let you upload articles on the fly within the Chat, so you can ask it questions
4. Make it embeddable in your site with one line of code
5. Let you update it for fun / with your branding
5. Enable syncing for any URLs you let us scrape, so that you can make sure it's always up to date
6. Let you upload multiple file types<p>I've been working on this for about a month now by myself and you can keep track of my feature updates here: <a href="https://libraria.dev/feature-updates" rel="nofollow">https://libraria.dev/feature-updates</a><p>I would LOVE your feedback on anything, and If you're willing to try it out I'm looking for a few beta users that can provide me more continuous feedback that I would gladly waive the fee for!
Show HN: Regex.ai – AI-powered regular expression generator
Regex.ai is an AI-powered tool that generates regular expressions. It can accurately generate regular expressions that match specific patterns in text with precision. Whether you're a novice or an expert, Regex.ai's intuitive interface makes it easy to input sample text and generate complex regular expressions quickly and efficiently. Overall, Regex.ai is a game-changer that will save you time and streamline your workflow.
Show HN: Regex.ai – AI-powered regular expression generator
Regex.ai is an AI-powered tool that generates regular expressions. It can accurately generate regular expressions that match specific patterns in text with precision. Whether you're a novice or an expert, Regex.ai's intuitive interface makes it easy to input sample text and generate complex regular expressions quickly and efficiently. Overall, Regex.ai is a game-changer that will save you time and streamline your workflow.
Show HN: Open AI is not Open – A browser extension
Show HN: Open AI is not Open – A browser extension
Show HN: GPT-4 Reverse Turing Test
Show HN: GPT-4 Reverse Turing Test
Show HN: GPT-4 Reverse Turing Test
Show HN: Apple Notes Liberator – Extract Notes.app Data and Save It as JSON
Hey there!<p>I just released the first version of a project I’ve been working on solves a very specific problem that perhaps only I have. I welcome any and all feedback, even if you just want to drop in to say that this is a hot piece of garbage!
Show HN: Apple Notes Liberator – Extract Notes.app Data and Save It as JSON
Hey there!<p>I just released the first version of a project I’ve been working on solves a very specific problem that perhaps only I have. I welcome any and all feedback, even if you just want to drop in to say that this is a hot piece of garbage!
Show HN: Apple Notes Liberator – Extract Notes.app Data and Save It as JSON
Hey there!<p>I just released the first version of a project I’ve been working on solves a very specific problem that perhaps only I have. I welcome any and all feedback, even if you just want to drop in to say that this is a hot piece of garbage!
Show HN: Generate styled web pages with just Python
There are a lot of Python to web app frameworks going around these days but I wanted something that was a little more lightweight that just generates HTML pages and can be embedded in Flask or other Python web servers incrementally.<p>PyVibe uses Python components to construct a page with styling that you can use in Flask, in a static site, or even in Pyodide.
Show HN: Finetune LLaMA-7B on commodity GPUs using your own text
I've been playing around with <a href="https://github.com/zphang/minimal-llama/">https://github.com/zphang/minimal-llama/</a> and <a href="https://github.com/tloen/alpaca-lora/blob/main/finetune.py">https://github.com/tloen/alpaca-lora/blob/main/finetune.py</a>, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU.<p>To prepare the data, simply separate your text with two blank lines.<p>There's an inference tab, so you can test how the tuned model behaves.<p>This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio.<p>Enjoy!
Show HN: Finetune LLaMA-7B on commodity GPUs using your own text
I've been playing around with <a href="https://github.com/zphang/minimal-llama/">https://github.com/zphang/minimal-llama/</a> and <a href="https://github.com/tloen/alpaca-lora/blob/main/finetune.py">https://github.com/tloen/alpaca-lora/blob/main/finetune.py</a>, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU.<p>To prepare the data, simply separate your text with two blank lines.<p>There's an inference tab, so you can test how the tuned model behaves.<p>This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio.<p>Enjoy!
Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
ChatLLaMA is an experimental chatbot interface for interacting with variants of Facebook's LLaMA. Currently, we support the 7 billion parameter variant that was fine-tuned on the Alpaca dataset. This early versions isn't as conversational as we'd like, but over the next week or so, we're planning on adding support for the 30 billion parameter variant, another variant fine-tuned on LAION's OpenAssistant dataset and more as we explore what this model is capable of.<p>If you want deploy your own instance is the model powering the chatbot and build something similar we've open sourced the Truss here: <a href="https://github.com/basetenlabs/alpaca-7b-truss">https://github.com/basetenlabs/alpaca-7b-truss</a><p>We'd love to hear any feedback you have. You can reach me on Twitter @aaronrelph or Abu (the engineer behind this) @aqaderb.<p>Disclaimer: We both work at Baseten. This was a weekend project. Not trying to shill anything; just want to build and share cool stuff.
Show HN: Get a Professional Headshot in Minutes with AI
After playing with AI Avatars (like many of us I guess around here), I started to wonder if we could instead bring real value to people by producing affordable professional head-shots using a combination of Dreambooth and ControlNet.<p>Obviously it's only the beginning and there are still many imperfections, but the foundational tech behind this (Dreambooth and ControlNet) are only respectively 6 months and 1.5 month old, and already delivers pretty amazing results.<p>I came up with this little service "Virtual Face" and I'm looking for feedback if some of you are willing to try it (you can use the HUNTER50 coupon to get 50% off, can't make it free to try yet since the running costs are still non-negligible).<p>Cheers,
Pierre
Show HN: Yaksha Programming Language
I have been working on this for a while. Main goal was to build a usable programming language. I even end up building few tools for this such as IntelliJ plugin, etc.<p>I also plan on building some games with it in future.<p>Main use case would be: small games (raylib), tools (static linux binaries with musl-libc) and recreational programming (wasm4). Works in Windows also. If you have emscripten in path you can even build these games/tools (raylib) to WASM.<p>Please have a look. Thank you.<p>-------------------------------------<p>Main Repo: <a href="https://github.com/YakshaLang/Yaksha">https://github.com/YakshaLang/Yaksha</a><p>Doc: <a href="https://yakshalang.github.io/documentation.html" rel="nofollow">https://yakshalang.github.io/documentation.html</a><p>Library: <a href="https://yakshalang.github.io/library-docs.html" rel="nofollow">https://yakshalang.github.io/library-docs.html</a><p>Tutorials: <a href="https://github.com/orgs/YakshaLang/discussions/categories/tutorials">https://github.com/orgs/YakshaLang/discussions/categories/tu...</a><p>----------------------------------------<p>Started after a comment from WalterBright here <a href="https://news.ycombinator.com/item?id=28929840" rel="nofollow">https://news.ycombinator.com/item?id=28929840</a>
Show HN: Yaksha Programming Language
I have been working on this for a while. Main goal was to build a usable programming language. I even end up building few tools for this such as IntelliJ plugin, etc.<p>I also plan on building some games with it in future.<p>Main use case would be: small games (raylib), tools (static linux binaries with musl-libc) and recreational programming (wasm4). Works in Windows also. If you have emscripten in path you can even build these games/tools (raylib) to WASM.<p>Please have a look. Thank you.<p>-------------------------------------<p>Main Repo: <a href="https://github.com/YakshaLang/Yaksha">https://github.com/YakshaLang/Yaksha</a><p>Doc: <a href="https://yakshalang.github.io/documentation.html" rel="nofollow">https://yakshalang.github.io/documentation.html</a><p>Library: <a href="https://yakshalang.github.io/library-docs.html" rel="nofollow">https://yakshalang.github.io/library-docs.html</a><p>Tutorials: <a href="https://github.com/orgs/YakshaLang/discussions/categories/tutorials">https://github.com/orgs/YakshaLang/discussions/categories/tu...</a><p>----------------------------------------<p>Started after a comment from WalterBright here <a href="https://news.ycombinator.com/item?id=28929840" rel="nofollow">https://news.ycombinator.com/item?id=28929840</a>
Show HN: Chatblade – A CLI Swiss Army Knife for ChatGPT
integrate chatGPT into your scripts or terminal work. Supports piping text, saving prompts, estimating costs, and some basic json/yaml extraction.<p>I've added some elaborate examples on the readme of how to use it with pictures, that may provide a better overview.
Show HN: Chatblade – A CLI Swiss Army Knife for ChatGPT
integrate chatGPT into your scripts or terminal work. Supports piping text, saving prompts, estimating costs, and some basic json/yaml extraction.<p>I've added some elaborate examples on the readme of how to use it with pictures, that may provide a better overview.