Show HN: Making Don Quijote accessible to Spanish learners https://ift.tt/JYjyfGw

Show HN: Making Don Quijote accessible to Spanish learners I love simple english wikipedia and I wanted to use that style of writing to make spanish books accessible to me. First I simplified the spanish[0] but simplification can't remove every word I don't know. This led me to adding the definition for words I probably wouldn't know[1]. Second simplifying the spanish ruined the magic of Don Quijote so I tried just adding definitions to the original[2]. The definitions aren't perfect but they let me stay in the flow of the text. I'm tempted to make a firefox extension to annotate any website so I can spend more time reading spanish. Let me know what you think! [0] https://ift.tt/1MXqo8z [1] https://ift.tt/x5u9gTr [2] https://ift.tt/t5BzRUi August 3, 2023 at 08:58PM

Show HN: TripClub – Plan Travel with AI https://ift.tt/C3prU8Y

Show HN: TripClub – Plan Travel with AI Hey HN! This is Will and Riley from TripClub ( https://tripclub.ai/ ). TripClub helps you plan and visualize your trips while giving you recommended itineraries to anywhere in the world based on your input. We began working on this when we couldn’t find a good solution to plan trips with friends, and found that most people we knew used something like google docs along with 24 tabs for researching places. Also, with the recent progress in generative AI, we found that we could now create detailed trips based on any input you’d like, and turn these into visually appealing itineraries. As you may have suspected, we primarily use openAI models for trip generation on the backend. We put the recommendations into an interactable map and itinerary. After creating a trip, you can add your friends so everyone can collaborate on editing the various places on your itinerary. Right now every aspect of the app is free and we hope to keep it that way. However we haven’t built in a source of revenue at the moment and are fully bootstrapped, so this could change (we plan to make revenue on hotel bookings in the future). We’re looking forward to hearing any of your comments, questions, and feedback! https://tripclub.ai/ August 3, 2023 at 09:06PM

Show HN: Learn languages through immersion with AI friends https://ift.tt/89GmBWV

Show HN: Learn languages through immersion with AI friends https://ift.tt/AeHs7mp August 3, 2023 at 07:26PM

Show HN: Using LLama2 to Correct OCR Errors https://ift.tt/wt5L1Dq

Show HN: Using LLama2 to Correct OCR Errors I've been disappointed by the very poor quality of results that I generally get when trying to run OCR on older scanned documents, especially ones that are typewritten or otherwise have unusual or irregular typography. I recently had the idea of using Llama2 to use common sense reasoning and subject level expertise to correct transcription errors in a "smart" way-- basically doing what a human proofreader who is familiar with the topic might do. I came up with the linked script that takes a PDF as input, runs Tesseract on it to get an initial text extraction, and then feeds this sentence-by-sentence to Llama2, first to correct mistakes, and then again on the corrected text to format it as markdown where possible. This was surprisingly easier than I initially expected thanks to the very nice tooling now available in libraries such as llama-cpp-python, langchain, and pytesseract. But the big issue I was encountering was that Llama2 wasn't just correcting the text it was given-- it was also hallucinating a LOT of totally new sentences that didn't appear in the original text at all (some of these new sentences used words which never appeared elsewhere in the original text). I figured this would be pretty simple to filter out using fuzzy string matching-- basically check all the sentences in the LLM corrected text and filter out sentences that are very different from any sentences in the original OCRed text. To my surprise, this approach worked very poorly. In fact, lots of other similar tweaks, including using bag-of-words and the spacy NLP library in various ways (spacy worked very poorly in everything I tried). Finally I realized that I had a good solution staring me in the face: Llama2. I realized I could get sentence level vector embeddings straight from Llama2 using langchain. So I did that, getting embeddings for each sentence in the raw OCRed text and the LLM corrected text, and then computed the cosine similarity of each sentence in the LLM corrected text against all sentences in the raw OCRed text. If no sentences match in the raw OCRed text, then that sentence has a good chance of being hallucinated. In order to save the user from having to experiment with various thresholds, I saved the computed embeddings to an SQLite database so they only had to be computed once, and then tried several thresholds, comparing the length of the filtered LLM corrected text to the raw OCRed text; if things worked right, these texts should be roughly the same length. So as soon as the filtered length dips below the raw OCRed text length, it backtracks and uses the previous threshold as the final selected threshold. Anyway, if you have some very old scanned documents laying around, you might try them out and see how well it works for you. Do note that it's extremely slow, but you can leave it overnight and maybe the next day you'll have your finished text, which is better than nothing! I feel like this could be useful for sites like the Internet Archive-- I've found their OCR results to be extremely poor for older documents. I'm very open to any ideas or suggestions you might have. I threw this together in a couple days and know that it can certainly be improved in various ways. One idea that I thought might be fun would be to make this work with a Ray cluster, sending a different page of the document to each of the workers in the cluster to do it all at the same time. https://ift.tt/6dOmpQg August 3, 2023 at 01:23AM

Show HN: We built swup+fragment-plugin to visually enhance classic websites https://ift.tt/D6vWdrK

Show HN: We built swup+fragment-plugin to visually enhance classic websites ## TL;DR - Progressively enhance your classic website / MPA to a single page app. - Support for fragment visits, comparable to nested routes in React or Vue. - Keep your site crawlable and indexable without any of the overhead of SSR. - No tight coupling of back- and frontend. Use the CMS / Framework / SSG of your choice. - Strong focus on interoperability with DOM-altering JS tools (think Alpine.js, jQuery, ...). - Strong focus on accessibility, even for fragment visits. ## Long Version: Best of three worlds Hi, I'm Rasso Hilber. I have been a web designer and developer since around 2004. From the beginning of my career, I always had to make tradeoffs between 3 goals when building websites: 1. The websites I build should be visually impressive, original, and snappy. 2. The websites I build should be crawlable, accessible and standards compliant. 3. The websites I build should have low technical complexity and be easy to maintain in the long run. In the beginning, I was able to achieve goals 1 (impressive!) and 3 (easy to maintain!) by using Macromedia/Adobe Flash, but due to the nature of the technology horribly failed to deliver crawlable and accessible websites. Later, I found a way to run two sites in parallel for each website I built, one using CMS-generated XHTML for crawlability, one in Flash for the visitors, fetching the data from its XHTML twin. Now I had solved goals 1 and 2, but my setup was awfully complex and brittle. Around 2010, I was relieved to see Flash finally coming to its end. I switched to building websites using PHP, HTML, and jQuery. I could now tick goals 2 (accessibility) and 3 (low complexity), but the websites I was able to build using these technologies weren't as impressive anymore. Hard page loads between every link click being one of the biggest regressions in UX from the days of Flash IMO. Around 2014/15, I first heard about the new frameworks: Angular, React, Vue. These frameworks were not intended to be used for classic websites. They were made for single-page-apps! But it felt to me like no one cared. Even when building classic websites, many developers sacrificed SEO and accessibility for a snappy experience, serving an empty `

` to the browser. I couldn't blame them; I had done the same in my early days as a Flash developer. They ticked goal 1 (impressive) and goal 3 (low complexity). But the lack of accessibility kept me from joining the movement. I was still building classic websites, after all. After some time, many started realizing that serving an empty div had downsides – SSR, hydration, and whatnot were born, now ticking goal 1 (impressive) and goal 2 (accessibility), with the trade-off of awful complexity. It reminded me a lot of my little Frankenstein's monster "Flash+XHTML," and I still didn't want to join the hype. Still, because the noise was so loud, I felt like I might be becoming obsolete, an "old man yelling at the clouds". New very interesting tools like HTMX or Unpoly popped up that looked promising at first, but at closer inspection weren't optimized for my use case either. These were primarily built for real interfaces/single-page-apps (html snippets instead of full pages, UI state independent of URLs, altered DOM saved in history snapshots, ...). I wanted to find a tiny tool, optimized for building presentational , content-driven websites with a strong focus on accessibility . Instead, after a few years of rolling my own home-grown solutions, I started using swup[0], a "Versatile and extensible page transition library for server-rendered websites". Swup consists of a tiny core and a rich ecosystem of official plugins[1] for additional functionality. It was hitting the sweet spot between simplicity and complexity, and felt like it was perfect for my use cases. Shortly after I had started using it, I became a core contributor and maintainer of swup. The only thing I was still missing to be a happy developer was the ability to create really complex navigation paths where selected fragments are updated as you navigate a site, much like nested routes allow in React or Vue. The last two months I teamed up with @daun [2] to finally solve this hard problem. The result is two things: 1. A new major release of swup (v4) that allows customizing the complete page transition process by providing a powerful hook system and a mutable visit object 2. The newly released fragment-plugin [3] that provides a declarative API for dynamically replacing containers based on rules Use cases for the fragment-plugin are: - a filter UI that live-updates its list of results on every interaction - a detail overlay that shows on top of the currently open content - a tab group that updates only itself when selecting one of the tabs - a form that updates only itself upon submission I can now finally build websites that tick all three boxes: 1. Visually impressive, fun, and snappy by using swup's first-class support for animations[4], cache[5], and preload capacities[6], enhanced with fragment visits as seen on the demo site. 2. Accessible by being able to serve server-rendered semantic markup that will fully work even with JavaScript disabled (try it out on the demo site!). On top of that, swup's a11y plugin[7] will automatically announce page visits to assistive technologies and will focus the new `

` element after each visit. 3. Because now all I need for my fancy frontend is a bit of progressive JavaScript, I can choose whatever tool I like on the server, keeping complexity low and maintainability high. I can use SSGs like eleventy or Astro (the demo site is built using Astro!), I can use any CMS like WordPress or ProcessWire, or a framework like Laravel. And I don't have to maintain an additional node server for SSG! The plugin is still in it's early stages, but I have a good feeling that this finally is the right path for me as a web developer. All it took was 20 years! ;) [0] https://ift.tt/dHK8hNx [1] https://ift.tt/jahtk8T [2] https://github.com/daun [3] https://ift.tt/7mYd8kJ [4] https://ift.tt/RLa4mTH [5] https://ift.tt/dTIXx6u [6] https://ift.tt/MQFjB4C [7] https://ift.tt/WNxMFY8 https://ift.tt/d5sfZO6 August 2, 2023 at 05:45PM

Show HN: Glo Dollar – the antipoverty stablecoin https://ift.tt/17S3u0t

Show HN: Glo Dollar – the antipoverty stablecoin Hi everyone! I just shipped a crypto project which I think all of you might actually like. It’s a digital dollar that helps end extreme poverty called Glo Dollar. We're backed by Sid Sijbrandij (GitLab). How it works: 1. You buy $1 Glo Dollar for $1 USD 2. Our partners invest the $1 USD in US Treasuries 3. Revenue we make we donate to a charity called GiveDirectly.org who use it to fund basic income programs for people in extreme poverty Note that you can _always_ redeem your $1 Glo Dollar for $1 USD again. We’re doing this because we believe stablecoins are a public good and should be managed as one. At the moment, the two big stablecoin companies are making record profits for a tiny group of shareholders instead. Tether, the issuer of USDT, shared profits of ~$1.5 billion in Q1 on assets under management of ~60 billion, with just ~50 people on staff. Even though its success is mostly attributable to the ecosystem’s adoption. Glo Dollar seeks to radically change this dynamic by repurposing its revenue to a good cause rather than risk/profit-seeking shareholders. At scale, we could lift millions of people out of extreme poverty. So even if you loathe crypto, we hope you at least appreciate what we’re trying to achieve. Very curious what y’all think :-)! https://ift.tt/dMVmnzW August 2, 2023 at 11:52PM

Show HN: Bookmarklet to open any web page in archive.is https://ift.tt/puSg5MK

Show HN: Bookmarklet to open any web page in archive.is This will bypass most paywalls. Simply make a new bookmark, edit it and paste in this code: javascript:(()=>{var url="https://archive.is/"+encodeURI(window.location.protocol + "//" + window.location.hostname + window.location.pathname); window.open(url, "_blank");})(); August 2, 2023 at 12:50AM

Show HN: Magic Loops – Combine LLMs and code to create simple automations https://ift.tt/oImaE1f

Show HN: Magic Loops – Combine LLMs and code to create simple automations Howdy! We built this as an experiment in personal-programming, combining the best of LLMs and code to help automate tasks around you. I personally use it to track the tides and get notified when certain conditions are met, something that pure LLMs had trouble dealing with and pure code was often too brittle for. We created it after getting frustrated with the inability of LLMs to deal with numbers and the various hoops we had to jump through to make ChatGPT output repeatable. At the core, Magic Loops are just a series of "blocks" (JSON) that can be triggered with different inputs (email, time, webhook), then operate on those inputs using a combination of LLMs and code, and then output those results (email, text, webhook). Under the hood, the LLM calls are using GPT-4 via OpenAI and the code is run in sandboxed (no internet) Docker containers in AWS. You have full control over each step of the loop, but you can also create (or attempt to create) a Magic Loop by simply describing what you want. We use GPT-4 to break that request into feasible steps, and then create a Magic Loop scaffold. Of course, you should still validate the loop before publishing it! We've seen some neat use cases already: - "Text me when the tide is less than 1ft between 7am and 7pm at Fort Funston" - "Summarize an email using this format and forward it to this address" - "Text me every time our store does more than $1000/day in volume on Shopify" - "Take specific data from Cloudflare, format it, and send it to Mixpanel every hour" We hope you enjoy what's essentially an experiment at this point. If folks like the concept, we're thinking about open sourcing it so you can run the loops locally with the code runtimes you wish (rather than in our code runners). Let us know what you think, and more importantly, what you wish to build or automate! Cheers, Adam & Mihai https://magicloops.dev August 1, 2023 at 10:27PM

Show HN: What you can do with 35 bytes of HTML and a single CSS file? https://ift.tt/BCMaoAD

Show HN: What you can do with 35 bytes of HTML and a single CSS file? Hi! Minimal code required to render an contentful and styled HTML page with CSS consists of these 35 bytes: In the submitted link I try to share with you how it works and what are the limitations of this hack I hope you have some fun with it :) Thanks Repo: https://ift.tt/qPwfyK1 https://ift.tt/e9iUjBu August 2, 2023 at 01:12AM

Show HN: IdentityLM, cryptographic proof of identity via language model output https://ift.tt/8hCaiy9

Show HN: IdentityLM, cryptographic proof of identity via language model output Hi HN, IdentityLM allows you to create text from a language model that is statistically signed by you, in a way that is computationally very hard to replicate, and computationally very easy to verify. It builds on current research around logit biasing, statistically advantaging certain tokens in a deterministic way. That research focuses on watermarking language model output to identify the model it came from. A really good paper about this idea was just awarded outstanding paper at ICML - https://ift.tt/u4MeHEh . I’ve basically taken that research and interpreted it in the context of public key cryptography. The readme of the github repo is basically small white paper describing how it works. Why should you care? First of all, we can fight scams and deepfakes with it which I know everyone is worried about with generative models becoming so good at simulating a politician, or writing convincing phishing emails and so on. Using speech-to-text it could also verify phone identities. Second, it’s allows transferable identity and trust across any internet platform. You can prove who you are anywhere, and link different profiles, just with natural text. Third, it allows extra encryption around pretty much anything. It adds an extra layer of proof to any interaction or communication. Love to have any comments or feedback! https://ift.tt/iNg3lSR August 2, 2023 at 01:06AM

Show HN: Your Open Source CV https://ift.tt/oy07MA5

Show HN: Your Open Source CV Hi HN! We launched Ringer last year and have been working hard on new features to support creators in Open Source. Today we're launching the Open Source CV. This is your complete history of contributions from GitHub in an easily shareable format. We're also making the code for the CV open source so that you can self-host: https://ift.tt/jJ91AXr Always happy to hear thoughts and suggestions! https://ift.tt/xnrt6qh August 1, 2023 at 07:39PM

Show HN: Web simulation of POP-CORN time service https://ift.tt/FizGxc0

Show HN: Web simulation of POP-CORN time service This replicates the experience of calling POP-CORN and having the current time read out by an Audichron. There is no commercial value here. It’s just some tech “art” for nostalgia purposes along with some history of popcorn. https://7672676.io/ August 1, 2023 at 09:24AM

Show HN: An MIT-licensed ChatGPT plugin that loads and edits files locally https://ift.tt/y4WcNRm

Show HN: An MIT-licensed ChatGPT plugin that loads and edits files locally https://ift.tt/5qRYVXc August 1, 2023 at 08:52AM

Show HN: Socket web extension – free NPM supply chain protection https://ift.tt/k5DtWgf

Show HN: Socket web extension – free NPM supply chain protection Hey HN, I'm Arjun, an 18-year-old intern at Socket. I've been working on a project that I'm really excited to share with you all - a browser extension that makes it easier to check the security of NPM packages before you use them. You can try the extension on any Chromium-based browser or on Firefox. - Chrome extension: < https://chrome.google.com/webstore/detail/socket-security/jb... > - Firefox add-on: < https://addons.mozilla.org/en-US/firefox/addon/socket-securi... > Socket scans NPM packages for malware, vulnerabilities, code smell, and unwanted behavior using AI and some very powerful in-house static analysis we've been perfecting over the last 2 years. As the primary developer of Parcel.js' web extension transformer (< https://parceljs.org/recipes/web-extension/ >), I thought it would be cool to use my own work on Parcel to create a useful extension during my internship at Socket. The extension displays scores alongside each package indicating quality, security, maintenance, and other useful metrics. It also tells you if a package accesses the network when it shouldn't need to, or if it runs malware in an install script. You can learn more about its features in my blog post: < https://socket.dev/blog/socket-web-extension > Feel free to ask any questions you have about Socket, the extension or even my work on Parcel. Excited to hear your feedback! - Arjun https://ift.tt/AjcV4Y9 August 1, 2023 at 04:23AM

Show HN: CocktailCMS – in-browser database with no login or servers required https://ift.tt/8eVf317

Show HN: CocktailCMS – in-browser database with no login or servers required During the lockdown in 2020, my girlfriend, an enthusiastic mixologist, needed a tool to organize her cocktail recipes and visualize the data. Traditional spreadsheets weren't cutting it due to the deeply nested data, and this struggle led me to create 'CocktailCMS'. Drawing inspiration from old-school databases like DBase, FoxPro, and MS Access, CocktailCMS is a browser-based database with features such as linking datasets and sub-tables. It's designed for local data storage in JSON format, but there's an option to sync with Google Drive for backup. Data can be exported in CSV and easily copy-pasted into visualizers. To give you an idea of what it can do, I've included two example datasets: a Game of Thrones one and another one on Mixology. The project is currently built in JS + Vue2. However, it does need a bit of renovation due to tech rot. I'm contemplating an upgrade to TS + Vue3, and also want to open source the project. But before I embark on this, I'm curious to gauge the community interest. Your feedback and suggestions are much appreciated! https://ift.tt/Bce20Ds August 1, 2023 at 04:50AM

Show HN: A Girl Next Door Does Not Exist (NSFW) https://ift.tt/wNtK8QJ

Show HN: A Girl Next Door Does Not Exist (NSFW) Warning: NSFW. I'm posting this from a throwaway. Note that on HN favorites are public, but upvotes are private. Porn seems like it'll be one of the big areas of ai in the short term. There've been multiple threads and comments about AI + Onlyfans and AI + porn and AI girlfriends on HN recently ( https://ift.tt/VMbNrDt , https://ift.tt/c2M70qE , https://ift.tt/ZCxfjWm ). I've heard that porn is the industry that pushes new technology forward - VHS, bluray, highly scalable video serving. I made a site compiling together some of the AI porn that I made with the help of some people on Discord over the past few months. I don't think AI will get rid of onlyfans. People spend on onlyfans for more than just the images. I do think people will have access to unlimited image and video porn at some point in the coming decade, which will definitely change the porn industry. The site shows what's possible with AI porn today - images both sfw and nsfw, audio, text, and some moving images. There's even more possible than just what's on the page, with lots of people are playing around with making animated gifs that are nsfw, there'll be animated 3d nsfw avatars, and so on. So the site isn't comprehensive at all. But it's still quite interesting. https://ift.tt/ev0dy4R August 1, 2023 at 04:04AM

Show HN: Openexus – Building blocks for the internet https://ift.tt/YqI8TPo

Show HN: Openexus – Building blocks for the internet Hi HN! We are thrilled to share a sneak peek of https://openexus.com after months of work. You can try out the cool demos on the front page! The idea is to build a platform and community for composable building blocks where anyone can easily create, find and connect different modules to create dynamic and interactive apps, sites, dashboards, and docs. This can be done without using a single line of code. Key principles of what we are building: 1) True composability that enables infinite possibilities — Modules today are either too complex to be used only by developers (e.g. NPM packages) or too simplistic where they are usually used as an embed in isolation. We are establishing a modularization foundation that is powerful enough for developers to express functionalities, simple enough for anyone (even kids) to use, and flexible enough to build sophisticated creations. 2) Smart connect without code — All logic can be clearly expressed by simply drawing lines. Depending on the data type and other characteristics of the connector, we can figure out how the connection should behave. For example, triggers can only be connected to actions, and data connectors that fetch from APIs can be defined as directional read-only connectors. 3) Open-connections for instant forking — Forking today is a time-consuming complex endeavor. Even a simple change requires many layers of code understanding. Instead of open-source code, we see a future of open-source connections, where remixing simply means adding new blocks and re-wiring them. What we are building can be described as NPM for non-developers, connectable Lego blocks for the Internet, or Minecraft for non-game creations. Our focus is to create a community where we can share ideas and innovations. We are super excited about the possibilities of this platform, especially when we incorporate AI. We will be releasing tutorials, opening up the playground, and sending out invites in the coming weeks. If you are eager to try out our tooling and create your own building blocks, drop us an email! We would love to hear your feedback! Website: https://openexus.com Email: m@openexus.com July 31, 2023 at 08:29AM

Show HN: YakshaLisp – Macros for Yaksha and Lisp Dialect https://ift.tt/4pm69ac

Show HN: YakshaLisp – Macros for Yaksha and Lisp Dialect YakshaLisp is a sub-language embedded in Yaksha compiler. Allowing you to do things like below (fizzbuzz). macros!{ (defun to_fb (n) (+ (if (== n 1) "" " ") (cond ((== 0 (modulo n 15)) "FizzBuzz") ((== 0 (modulo n 3)) "Fizz") ((== 0 (modulo n 5)) "Buzz") (true (to_string n)) ))) (defun fizzbuzz () (list (yk_create_token YK_TOKEN_STRING (reduce + (map to_fb (range 1 101)))))) (yk_register {dsl fizzbuzz fizzbuzz}) } def main() -> int: println(fizzbuzz!{}) return 0 This is available in latest release - https://ift.tt/XATF6xd (I recommend using release.py in compiler/scripts if you want to locally compile it) Few more examples: - embedding a text file macros! { (defun load_string (file) (list (yk_create_token YK_TOKEN_STRING (io_read_file (map_get file "value"))))) (yk_register {dsl load_string load_string}) } def main() -> int: println(load_string!{"test.txt"}) return 0 - importing a macro import import_me as magic def main() -> int: println(magic.counter!{}) println(magic.counter!{}) println(magic.counter!{}) return 0 Looking for ideas/advice/criticism :) https://ift.tt/mHwdu6R July 31, 2023 at 04:30PM

Show HN: LearnLingo – Converse with an AI-powered language tutor https://ift.tt/VCDfiLR

Show HN: LearnLingo – Converse with an AI-powered language tutor Hey folks! I'm Callum, and I'm working on a way to practice a new language with an AI powered tutor. I've always found that the hardest part of learning a new language is finding someone to actually converse with. Even if a partner can be found, the pressure can mean that you are more focused on not making mistakes than on actually learning new grammar or vocabulary. The service that I have been working on allows you to practice with a language tutor via online chat messages, or you can have a turn-based voice conversation. I'm working on a number of other features that will be coming out shortly, including a few games for practising pronunciation and listening skills, as well as a plan to release some lesson plans for specific languages later on. Have a try, and let me know if you have any feedback! https://ift.tt/P3J96l5 July 31, 2023 at 11:06AM

Show HN: pff - Modern ping alternative to check your internet connection quality https://ift.tt/UDNYB8g

Show HN: pff - Modern ping alternative to check your internet connection quality Hi, you can examine your internet connection quality and status in terminal using this small tool I created last year See a preview on asciinema: https://ift.tt/LceCOgl I hope you find it useful. Thanks :) https://ift.tt/tqh7KAy July 31, 2023 at 01:45AM