The best Hacker News stories from Show from the past week
Latest posts:
Show HN: Aviation navigation log on $20 receipt printer
Show HN: Aviation navigation log on $20 receipt printer
Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
CSS Selectors: A Visual Guide
Show HN: AI-town, run your own custom AI world SIM with JavaScript
Hi HN community! We want to share AI-town, a deployable starter kit for building and customizing your own version of AI simulation - a virtual town where AI characters live, chat and socialize.<p>Inspired by great work from the Stanford Generative Agent paper (<a href="https://arxiv.org/abs/2304.03442" rel="nofollow noreferrer">https://arxiv.org/abs/2304.03442</a>).<p>A few features:
- Includes a convex.dev backed server-side game engine that handles global state
- Multiplayer ready. Deployment ready
- 100% Typescript
- Easily customizable. You can fork it, change character memories, add new sprites/tiles and you have a custom AI simulation<p>The goal is to democratize building your own simulation environment with AI agents. Would love to see the community build more complex interactions on top of this. Let us know what you think!<p>Demo: <a href="https://www.convex.dev/ai-town" rel="nofollow noreferrer">https://www.convex.dev/ai-town</a><p>I made a world Cat Town to demonstrate how to customize AI town. Using C(h)atGPT :)<p>Demo: <a href="https://cat-town.fly.dev/" rel="nofollow noreferrer">https://cat-town.fly.dev/</a>
Code: <a href="https://github.com/ykhli/cat-town">https://github.com/ykhli/cat-town</a>
Show HN: Little Rat – Chrome extension monitors network calls of all extensions
Hi HN<p>I needed a way to monitor network calls made by chrome extensions so I made a small extension.<p>You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review.<p>Hopefully it's useful to others.<p><a href="https://github.com/dnakov/little-rat">https://github.com/dnakov/little-rat</a><p><a href="https://twitter.com/dnak0v" rel="nofollow noreferrer">https://twitter.com/dnak0v</a>
Show HN: LLMs can generate valid JSON 100% of the time
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming.<p>Recently we came up with a fast way to generate text that matches a regex (<a href="https://blog.normalcomputing.ai/posts/2023-07-27-regex-guided-generation/regex-guided-generation.html" rel="nofollow noreferrer">https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...</a>). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We can transform this DFA into a generative model: in each state we get a list of symbols which correspond to completions that partially match the regular expression. We mask the other symbols in the logits returned by a large language model, sample a new symbol and move to the next state. The subtelty is that language models work with tokens, not symbols, so we derive a new FSM whose alphabet is the model's vocabulary. We can do this in only one pass over the vocabulary.<p>Generating the token masks thus only requires a dictionary lookup at each state. Our method blows other libraries like Microsoft's guidance out of the water.<p>From there it was only a small leap to be able to generate text that follows a JSON schema (<a href="https://json-schema.org/" rel="nofollow noreferrer">https://json-schema.org/</a>), or is parseable into a Pydantic model (<a href="https://docs.pydantic.dev/latest/usage/models/" rel="nofollow noreferrer">https://docs.pydantic.dev/latest/usage/models/</a>). The method works with union types, optional types, nested schemas, arrays, everything. It is guaranteed that the output is parseable.<p>I think it's cool, and I've spent a lot of time watching even tiny models output valid JSON over the weekend. Hope you will too.<p>I look forward to feedback, bug reports, feature requests and discussions!<p>Edit: Link to our pre-print explaining the method and how this can be extended to generate text that follows a Context-Free Grammar <a href="https://arxiv.org/abs/2307.09702" rel="nofollow noreferrer">https://arxiv.org/abs/2307.09702</a>
Show HN: I wrote a RDBMS (SQLite clone) from scratch in pure Python
I wrote a relational database management system (RDBMS) (sqlite clone) from scratch in pure Python.
Show HN: I wrote a RDBMS (SQLite clone) from scratch in pure Python
I wrote a relational database management system (RDBMS) (sqlite clone) from scratch in pure Python.
Show HN: Pip Imports in Deno
deno_python 0.3.1 adds support for importing python pip packages directly in JavaScript! Fun and useful, slightly cursed.
Show HN: Tetris, but the blocks are ARM instructions that execute in the browser
OFRAK Tetris is a project I started at work about two weeks ago. It's a web-based game that works on desktop and mobile. I made it for my company to bring to events like DEF CON, and to promote our binary analysis and patching framework called OFRAK.<p>In the game, 32-bit, little-endian ARM assembly instructions fall, and you can modify the operands before executing them on a CPU emulator. There are two segments mapped – one for instructions, and one for data (though both have read, write, and execute permissions). Your score is a four byte signed integer stored at the virtual address pointed to by the R12 register, and the goal is to use the instructions that fall to make the score value in memory as high as possible. When it's game over, you can download your game as an ELF to relive the glory in GDB on your favorite ARM device.<p>The CPU emulator is a version of Unicorn (<a href="https://www.unicorn-engine.org/" rel="nofollow noreferrer">https://www.unicorn-engine.org/</a>) that has been cross-compiled to WebAssembly (<a href="https://alexaltea.github.io/unicorn.js/" rel="nofollow noreferrer">https://alexaltea.github.io/unicorn.js/</a>), so everything on the page runs in the browser without the need for any complicated infrastructure on the back end.<p>Since I've only been working on this for a short period of time leading up to its debut at DEF CON, there are still many more features I'd eventually like to implement. These include adding support for other ISAs besides ARM, adding an instruction reference manual, and lots of little cleanups, bug fixes, and adjustments.<p>My highest score is 509,644,979, but my average is about 131,378.<p>I look forward to feedback, bug reports, feature requests, and strategy discussions!
Show HN: Tetris, but the blocks are ARM instructions that execute in the browser
OFRAK Tetris is a project I started at work about two weeks ago. It's a web-based game that works on desktop and mobile. I made it for my company to bring to events like DEF CON, and to promote our binary analysis and patching framework called OFRAK.<p>In the game, 32-bit, little-endian ARM assembly instructions fall, and you can modify the operands before executing them on a CPU emulator. There are two segments mapped – one for instructions, and one for data (though both have read, write, and execute permissions). Your score is a four byte signed integer stored at the virtual address pointed to by the R12 register, and the goal is to use the instructions that fall to make the score value in memory as high as possible. When it's game over, you can download your game as an ELF to relive the glory in GDB on your favorite ARM device.<p>The CPU emulator is a version of Unicorn (<a href="https://www.unicorn-engine.org/" rel="nofollow noreferrer">https://www.unicorn-engine.org/</a>) that has been cross-compiled to WebAssembly (<a href="https://alexaltea.github.io/unicorn.js/" rel="nofollow noreferrer">https://alexaltea.github.io/unicorn.js/</a>), so everything on the page runs in the browser without the need for any complicated infrastructure on the back end.<p>Since I've only been working on this for a short period of time leading up to its debut at DEF CON, there are still many more features I'd eventually like to implement. These include adding support for other ISAs besides ARM, adding an instruction reference manual, and lots of little cleanups, bug fixes, and adjustments.<p>My highest score is 509,644,979, but my average is about 131,378.<p>I look forward to feedback, bug reports, feature requests, and strategy discussions!
Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI
Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI
Show HN: Get notified when sites update their terms of service
After reading about what happened with NightOwl yesterday [0], I thought about what it would take to be aware of things like that in the future. I created ToSNotify to automatically notify you when a website's terms change.<p>A harder problem I've been thinking through is how to know which terms to track, since it'd be a pain to add every site I have an account with. One idea I had is to automatically get terms for apps you have installed from the app store. Any other ideas/feedback are appreciated!<p>[0]: <a href="https://news.ycombinator.com/item?id=37052508">https://news.ycombinator.com/item?id=37052508</a>
I'm 17 and wrote this guide on how CPUs run programs
Show HN: Easyful – A Free Gumroad Alternative
Hi HN,<p>If you’re selling templates or digital assets online, platforms like Gumroad have a ton of amazing features . . . but they’re also expensive. It’s not uncommon to be paying 10%, 20% or even 30% of your revenue just to host and deliver some digital content to customers.<p>Instead, we think most creators should own their own Stripe account and use a lightweight fulfillment layer to send customers their orders.<p>So we built Easyful, a platform built on Stripe to email your content to customers when they buy it. And it’s free!<p>We’ve been using Easyful ourselves for a few months now. Try it out and let us know what you think!
Show HN: Chat with your data using LangChain, Pinecone, and Airbyte
Hi HN,<p>A few of our team members at Airbyte (and Joe, who killed it!) recently played with building our own internal support chat bot, using Airbyte, Langchain, Pinecone and OpenAI, that would answer any questions we ask when developing a new connector on Airbyte.<p>As we prototyped it, we realized that it could be applied for many other use cases and sources of data, so... we created a tutorial that other community members can leverage [<a href="http://airbyte.com/tutorials/chat-with-your-data-using-openai-pinecone-airbyte-and-langchain">http://airbyte.com/tutorials/chat-with-your-data-using-opena...</a>] and the Github repo to run it [<a href="https://github.com/airbytehq/tutorial-connector-dev-bot">https://github.com/airbytehq/tutorial-connector-dev-bot</a>]<p>The tutorial shows:
- How to extract unstructured data from a variety of sources using Airbyte Open Source
- How to load data into a vector database (here Pinecone), preparing the data for LLM usage along the way
- How to integrate a vector database into ChatGPT to ask questions about your proprietary data<p>I hope some of it is useful, and would love your feedback!
Show HN: Doculite – Use SQLite as a Document Database
Hi!<p>As I was working on a side project, I noticed I wanted to use SQLite like a Document Database on the server.
So I built Doculite. DocuLite lets you use SQLite like Firebase Firestore. It's written in Typescript and an adapter on top of sqlite3 and sqlite.<p>Reasons:<p>1) Using an SQL Database meant having less flexibility and iterating slower.<p>2) Alternative, proven Document Databases only offered client/server support.<p>3) No network. Having SQLite server-side next to the application is extremely fast.<p>4) Replicating Firestore's API makes it easy to use.<p>5) Listeners and real-time updates enhance UX greatly.<p>6) SQLite is a proven, stable, and well-liked standard. And, apparently one of the most deployed software modules right now. (src: <a href="https://www.sqlite.org/mostdeployed.html" rel="nofollow noreferrer">https://www.sqlite.org/mostdeployed.html</a>)<p>What do you think? Feel free to comment with questions, remarks, and thoughts.<p>Happy to hear them.<p>Thanks
Show HN: Phind V2 – A GPT-4 agent that’s connected to the internet and your code
Hi HN - Today we’re launching V2 of Phind.com, an assistant for programmers that combines GPT-4 with the ability to search the web and your codebase to solve nearly any technical problem – no matter how difficult.<p>We’re incredibly grateful for the feedback we received when we first launched GPT-4 answers back in April (<a href="https://news.ycombinator.com/item?id=35543668">https://news.ycombinator.com/item?id=35543668</a>). As Phind has gotten better at complex programming tasks, the questions it gets asked have gotten more complex as well. In the past, we would always perform a web search for every input. This limitation constrained Phind’s answers to what was present in the search results, preventing us from making Phind a more powerful debugger and making it challenging to integrate Phind with your codebase.<p>We’ve addressed all these shortcomings in Phind V2. This release has three major updates: (1) Phind is now a pair programming agent that knows when to browse the web, ask clarifying questions, and call itself recursively; (2) the answering engine defaults to GPT-4, and you can use it without a login; (3) we integrate with your codebase via our new VS Code extension.<p>We realized that search is only one of many tools that Phind should be able to use. As such, Phind has been re-engineered to be an agent that can dynamically choose whatever tool best helps the user – it’s now smart enough to decide when to search and when to enter a specialized debug mode. Instead of making assumptions about your code and proceeding blindly, Phind can ask you questions and clarify its assumptions. When a problem requires multiple searches or logical steps to solve, Phind can call itself recursively and perform multi-step reasoning without user input.<p>We’ve heard from you that switching between your IDE and Phind in the browser has been a major pain point. No longer – we’re launching a VS Code extension that brings Phind into the IDE and finally connects Phind with the context of your codebase. Phind in VS Code automatically determines which parts of your code are relevant to your search and can help you squash bugs in a single click.<p>To maximize Phind’s alignment with your preferred answer style, we’ve also added a feature called Answer Profile where you can tell the AI about yourself. Phind will apply this answering style across the board, automatically.<p>Here are some examples of the new Phind answering questions it could not before:<p>Clarifying assumptions to help a user with debugging: <a href="https://www.phind.com/agent?cache=cljmjzjgn0000jo085otq111f">https://www.phind.com/agent?cache=cljmjzjgn0000jo085otq111f</a><p>Designing a highly specific and custom database schema: <a href="https://www.phind.com/agent?cache=clkwpprz600g4jt08dl21e7r6">https://www.phind.com/agent?cache=clkwpprz600g4jt08dl21e7r6</a><p>Splitting a Wordpress theme across multiple files: <a href="https://www.phind.com/agent?cache=clknqywuq001pji083sdacf9p">https://www.phind.com/agent?cache=clknqywuq001pji083sdacf9p</a><p>Phind’s asking clarification questions in debug mode: <a href="https://www.phind.com/agent?cache=cljmjzjgn0000jo085otq111f">https://www.phind.com/agent?cache=cljmjzjgn0000jo085otq111f</a><p>Phind extension answering questions about a local codebase: <a href="https://www.phind.com/agent?cache=ra4kh2v3epgv5iw7z6dlzuo4">https://www.phind.com/agent?cache=ra4kh2v3epgv5iw7z6dlzuo4</a><p>Answering questions about a local codebase using the web: <a href="https://www.phind.com/agent?cache=ztiaju6xwtpi39l2kjdnwh20">https://www.phind.com/agent?cache=ztiaju6xwtpi39l2kjdnwh20</a><p>We are incredibly grateful for the feedback the HN community has given us and are excited to hear your thoughts about this release!<p>Cheers,
Michael and Justin