-->
Welcome to today’s roundup of the most popular Show HN projects for 2024-09-14. From innovative AI applications to practical development tools, these projects showcase the creativity and vitality of the tech community. Let’s explore these exciting new inventions together!
作者: mxsjoberg
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://1fw.world
Author: keepamovin
热门程度: 1 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/dleemiller/WordLlama
作者: deepsquirrelnet
请提供需要翻译的文本。: After working with LLMs for long enough, I found myself wanting a lightweight utility for doing various small tasks to prepare inputs, locate information and create evaluators. This library is two things: a very simple model and utilities that inference it (eg. fuzzy deduplication). The target platform is CPU, and it’s intended to be light, fast and pip installable — a library that lowers the barrier to working with strings semantically. You don’t need to install pytorch to use it, or any deep learning runtimes.
How can this be accomplished? The model is simply token embeddings that are average pooled. To create this model, I extracted token embedding (nn.Embedding) vectors from LLMs, concatenated them along the embedding dimension, added a learnable weight parameter, and projected them to a smaller dimension. Using the sentence transformers framework and datasets, I trained the pooled embedding with multiple negatives ranking loss and matryoshka representation learning so they can be truncated. After training, the weights and projections are no longer needed, because there is no contextual calculations. I inference the entire token vocabulary and save the new token embeddings to be loaded to numpy.
While the results are not impressive compared to transformer models, they perform well on MTEB benchmarks compared to word embedding models (which they are most similar to), while being much smaller in size (smallest model, 32k vocab, 64-dim is only 4MB).
On the utility side, I’ve been adding some tools that I think it’ll be useful for. In addition to general embedding, there’s algorithms for ranking, filtering, clustering, deduplicating and similarity. Some of them have a cython implementation, and I’m continuing to work on benchmarking them and improving them as I have time. In addition to “standard” models that use cosine similarity for some algorithms, there are binarized models that use hamming distance. This is a slightly faster, similarity algorithm, with significantly less memory per embedding (float32 -> 1 bit).
Hope you enjoy it, and find it useful. PS I haven’t figured out Windows builds yet, but Linux and Mac are supported.
受欢迎程度: 153 points | 7 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://chromewebstore.google.com/detail/add-to-sheets-save-to-goo/hgilhmbegaanegfbcppneigcmhgoinib
作者: siegers
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.beyondacres.co
作者: cgarvis
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://noporn.net
作者: Alan_Swift
Could you please provide the text you would like me to translate?: The Need I Discovered:
While talking with friends and community members, I noticed that many people struggle with maintaining their NoFap commitment and recovering from addiction. They often need better tools to help them resist temptation and stay on track.
Understanding the Need:
I realized that people often face distractions, especially online, which can undermine their efforts to stay committed. I believed that a browser extension designed to block harmful content and provide additional support could make a significant difference in their recovery journey.
Development Process:
Based on this need, I spent three days developing a solution. Throughout this time, I encountered several challenges, particularly with effectively identifying and blocking inappropriate content. After overcoming these hurdles, I incorporated additional features to enhance user support.
Product Features:
This Chrome extension not only blocks harmful content but also provides daily reminders and tracks recovery progress. It’s designed to support NoFap goals and offer extra encouragement to users throughout their recovery journey.
Feedback Request:
I invite everyone to try out this extension and provide feedback. Your insights will be invaluable in refining the product and helping others who are working towards overcoming addiction.
受欢迎程度: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://pod-transcriber-qa-artwest.replit.app
作者: westche2222
人气: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/benrules2/insta2000
作者: benrules2
Could you please provide the text you want me to translate?: I’ve been avoiding instagram for a few years, as it feels very noisy and addictive. I’m starting to feel out of touch from friends though, so got wondering if I could build a tool to get just my friends updates, without all the other junk.
It turns out scraping my own profile and re-rendering a static webpage is quite a successful way to achieve that goal. It has no ads, no discovery injections, no trackers, no infinite scroll, no notifications. It does include stories and posts alongside each other. It does sort things based on recent updates. In the end, it proved better than I expected with a relatively small effort. I made it retro as well just for a fun throwback, and as a protest against the modern web!
It leans very heavily on the [instaloader package](https://instaloader.github.io/)and I’m quite grateful for the contributors there!
Repo is yours to use and build on, and feel free to contribute as well.
受欢迎程度: 4 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://multimodal-demo.milvus.io/
作者: codingjaguar
It seems like you didn’t provide a specific text to translate. Could you please provide the text you would like me to translate?: The recent progress in multi-modality retrieval is to augment image search with text instruction, so called Composite Image Retrieval (CIR). Related research includes https://huggingface.co/BAAI/bge-visualized and Google’s https://open-vision-language.github.io/MagicLens/. We built a live demo for people to play with it and get a feeling of the quality of this retrieval approach.
Popularité: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://mapli.st
作者: MapList
It seems you would like a translation for the term “Description.” Could you please provide more context or the full text you want translated?: I’d love your feedback on my latest project.
To try it for free, simply reply “@maplistbot create a list” to any thread with place recommendations. The bot will reply with a Google Maps link to your newly created list of places.
If you like it and want to explore the Pro features, use the code PH40 for a 40% discount. Pro Features include:
Popularity: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/orf/docker-repack
作者: orf
Popularity: 9 points | 4 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.listennotes.com/api/
作者: wenbin
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/lets-all-be-stupid-forever/circuit-artist
作者: rafinha
It seems that “Description” is a bit too vague for me to provide a translation. Could you please provide more context or the specific text you would like translated?: Inspired by games like Turing Complete/Virtual Circuit Board/Logic World, I tried to make a mix of aseprite and wiredworld/wired-logic, the idea being the user can build a digital circuit using a “fullstack” pixelart creation workflow.
The circuit is just an image. The primitives are (i) connected wires which have undefined, 0 or 1 state during simulation (displayed brighter or darker in function of the state) and (ii) NANDs, which are little pixel triangles. During simulation the user can interact with any wire by clicking on it, toggling its state, which is cool for messing around when learning. The simulation uses a unit-delay event driven algorithm.
Then, on top of that there are little wire interfaces on the left side of the image that communicate with an external system. This external system is defined in lua and is simulated together with the main circuit (they alternate until convergence). By default there’s a sandbox mode with a clock and a power-on-reset signal. The user can choose other “levels”, where the API change and there are some problems to solve, from finding if a number is multiple of 3 to solving hanoi tower to finding if a number is prime. The idea is that if the user want to learn but not sure what to do they can try to solve these puzzles, or they can change the lua scripts to add their own stuff/interface for a custom project.
I’ve also included a small wiki (circuitopedia) with some basic digital concepts to guide those who are new or are a bit rusty. It’s not super detailed but I guess it can at the very least present the concepts so the user can dig further on more serious material if they want to.
I developed the game in C with raylib, with scripting in lua/luajit. I’ve put the game on steam (for windows) and released the source code on github under GPLv3. There’s also a web demo version on itch.io, even though it’s a bit laggy: https://lets-all-be-stupid-foreva.itch.io/circuit-artist-dem… .
Feedback is appreciated!
受欢迎程度: 51 points | 2 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/clemensmanert/dotfiles
作者: seg_fault
Please provide the text you would like translated, and I’ll be happy to assist you!: I developed a solution to manage color themes for my dotfiles efficiently. By using a Makefile alongside the Mustache templating engine, I can switch between a dark theme for nighttime and a light theme for daytime with a single command.
Each color theme is defined in its own file, allowing for easy creation of new themes without the need to modify every individual dotfile. This approach streamlines the process of theme management across my configurations.
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
作者: Smiler_
It seems you’ve only provided the word “Description.” Could you please provide the text you would like me to translate?: Hello, HN! After weeks of being frustrated with bloated software and AI writing tools, I decided to make something different—something simpler. That’s how I created Fleschkey, my privacy-first, AI-free text editor.
Fleschkey is for writers who want their work to be clear. It gives instant feedback with a readability score based on the Flesch-Kincaid formula, made in 1975—a system that’s been used in many ways since then.
To me, privacy means more than opting in or out. It means no one can see or take your data unless there’s a good reason. That’s why everything stays on your device—no cloud, no AI, no data collection, no worries.
By the way, the text above received the following scores: Flesch-Kincaid Grade Level: 7.16 Flesch Reading Ease Score: 67.55 Reading Level: 7th grade (Plain English) Average Words per Sentence: 13.38 Average Syllables per Word: 1.49 Sentences: 8 Words: 107 Characters (including spaces): 639
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.dateready.pro
作者: marvit
Sure, please provide the text that you would like me to translate.: Hey HN,
I’m a guy who noticed how challenging dating and conversations have become, especially after COVID. I’ve personally felt the nerves and stress, and I’ve seen friends struggle to express themselves even when they know what they want to say.
So, I built DateReady—an AI-powered conversation game where you can practice real-life dating scenarios and receive instant feedback. The idea is to help people get comfortable with those first steps in a fun and interactive way.
DateReady features:
Get Her Contact: Navigate through 8 levels, each presenting a unique scenario and character with their own personalities, insecurities, and dreams. After each level, you’ll receive feedback on different aspects of your approach, contributing to your XP points. You have 5 minutes per level—unlock the next one by succeeding, or lose a life if you don’t.
Get Ready: A practice mode to test your conversation skills on various topics for a real date, with helpful tips from a virtual wingman to improve each interaction.
First 3 lives to play are free! I’d love to hear your thoughts and feedback!
人气: 4 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/shermp/Pico-ASHA
作者: shermp
Please provide the text you would like me to translate.: The past several months, I have been developing a method of streaming audio to my hearing aids from a PC. To do this, I have programmed a Pi Pico W to act as a USB audio device which will work with any OS and be capable of playing audio on my hearing aids.
For a bit of background, modern hearing aids have different methods of directly streaming audio over bluetooth. The earliest (and most common) is Apple’s Made for iPhone program. Phonak hearing aids use bluetooth classic (A2DP). Many devices support Android’s Audio Streaming for Hearing Aids (ASHA). And the latest hearing aids are beginning to support the new LE Audio standard.
The goal of Pico-ASHA is to implement Android’s ASHA. Android has published a specification at https://source.android.com/docs/core/connect/bluetooth/asha. The reference implementation is in the AOSP project.
Pico-ASHA presents itself as USB headset (and a CDC serial device) to the OS. Apart from the Pico W, no additional hardware is required. Pairing to hearing aids is automatic, and once paired, audio streaming Just Works (tm) - in theory! The project is implemented using the Pico C/C++ SDK, including TinyUSB for the USB audio/CDC support, and btstack for the Bluetooth LE stack.
I have now reached the stage of the project where it (mostly) works well with my own hearing aids (Oticon More 2). I would like to expand testing to other hearing aid makes and models, because I have probably made assumptions that work with my hearing aids, but not others. If anybody with suitable hearing aids who have (or can obtain) a Pico W and are willing to be an early tester, it would be much appreciated. I would hate for this to be an Oticon More only project.
The motivation for working on this is pretty simple - the adapters hearing aid manufactures provide for interfacing with computers are outrageously priced. I object to paying them hundreds of dollars for commodity hardware. Also, it’s been a great challenge.
This is my first ever attempt at developing on a microcontroller, on USB device support, and bluetooth. So please forgive the state of the codebase, I was learning how to do stuff as I went along.
Finally, I would like to acknowledge the recent work occurring in the Linux space to add experimental ASHA support to BlueZ (https://github.com/bluez/bluez/pull/836) and a pipewire implementation (https://github.com/thewierdnut/asha_pipewire_sink). Both projects reignited my enthusiasm to continue work on Pico-ASHA.
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.figma.com/community/plugin/1413574934305847457/token-swapper
作者: edgarasben
I’m sorry, but it seems like the text you want translated is missing. Could you please provide the content that needs translation?: Hi everyone,
I’ve created a new Token Swapper plugin for Figma to address limitations I encountered while working on a multi-brand mobile app UI. The Figma’s Pro plan’s 4 Modes (or even the Enterprise plan’s 40 Modes) weren’t sufficient for my needs.
I made Token Swapper to quickly switch between themes (based on variables and styles) without relying on Modes. The only requirement is that you organize your themes in top-level folders within both the variables and styles sections.
I’d love for you to try it out and share your thoughts. Your feedback is appreciated!
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
作者: Marius_Manola
Please provide the text you would like me to translate.: I thought to make a funny website with a fine-tuned model that acts like the guide from Douglas Adams’s novel. This way, you can find the right answer when in a tight spot (like when you need a ride to Alpha Centauri or smth).
人气: 55 points | 11 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://gerg.cafe
作者: jer0me
Please provide the text you would like me to translate.: I built this website for my sister’s birthday to replace the Apple note she had been keeping on her phone. We both post reviews, and it’s a nice way to stay connected with a shared project while I’m at college across the country.
Tech specs: A simple custom CMS built with Laravel, Livewire, Tailwind, and SQLite hosted on a shared $5 Hetzner box, deployed with Forge.
In this context, “Popularity” can be translated as “受欢迎程度.”: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://growpi.fun/
作者: error404x
The text provided does not contain any specific content to translate. Please provide the text you’d like me to translate, and I’ll be happy to help!: Hey HN,
I’ve built GrowPi, a fun real-time app where every click from visitors adds one decimal place to Pi. Watch the decimal expansion live as people around the world contribute
I would love to hear your feedback!
Thanks.
人气: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://tools.adrium.dev/timer.html
作者: adrium
Please provide the text you would like translated.: Granted, there are countless workout and pomodoro timers around. However, if I liked one, it still had a feature missing that I really liked from a different one. Ads and paid apps were a no go, too. So I was inspired by many of them to create my own.
Primarily, I wanted sounds, good visibility, customizable sequences, and good usability on mobile.
I am doing one workout almost daily, so I use it very often. I have a couple of routines ranging from 4 to 20 minutes. When I am changing routines after some months, I need to memorize them first. Therefore, I wanted to be able to name the intervals.
Other features include:
- Sequence editor that helps efficiently creating alternating and numbered intervals.
- Background color changes depending on a work/rest type of interval. Sometimes I am listening to music through a different device and miss the countdown. With the colors changing and the progress circle, it is easy to recongnize, if the work or rest interval has already started.
- Light and Dark modes are kind of a must have for every app nowadays.
- Progress circles are more accurate to estimate from afar than bars plus they give a nice visual touch.
- Detailed timing that includes the wall time when the workout is finished. Sometimes I am in a bit of a rush before taking a shower. With that display, it is easier to see, if I still have time for a workout.
- Intervals can easily be skipped, restarted, and repeated.
- There are a set of sounds to choose from: workout, breathe, or none.
- I discovered that browsers now even have speech synthesis APIs. The timer will tell you what the upcoming interval will be, so you never have to check the display.
- System notifications are triggered for longer intervals as used in the pomodoro technique.
It is pretty much feature complete now. I want to add an import/export feature in the near future though.
However, please let me know what you are still missing to make it your preferred timer!
Depending on the platform, the timer may not play sounds anymore when put in the background. I have found that the timing of the sounds also depend on the network quality. In any case, it will resume counting correctly when re-opening it in the foreground.
The source code is just one short html file that can be loaded into the browser. Hence, it’s open source. I am not a dev anymore, but I love how cross-platform applications can be built with web technologies nowadays. I like Vue.js for its simplicity to create dynamic templates.
Popularity: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://apps.apple.com/us/app/preppr-learn-stock-survive/id6670330104
作者: anujsjpatel
Please provide the text you’d like me to translate, and I’ll be happy to help!: Hi, this is my first iOS app and built it for the prepping community as I saw all their existing apps looked like they were from 2010 :)
It’s 80-90% free (unless you are a power user e.g. create a lot of AI generated items, then there is a cheap pro plan).
Enjoy!
受欢迎程度: 13 points | 5 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/john-friedman/datamule-python
作者: jgfriedman1999
Sure! Please provide the text you would like me to translate, and I’ll be happy to assist.: Features:
Datasets:
Datasets can be downloaded using the package, or here https://www.dropbox.com/scl/fo/byxiish8jmdtj4zitxfjn/AAaiwwu…
All APIs are free and do not require auth, so you can use them directly :)
e.g. I’m currently using the parser api with js to run my filing viewer demo: https://datamule.xyz/filings_viewer
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/phiresky/thought-forge-ai
作者: phiresky
Please provide the text you would like to have translated.: I’ve recently seen a fair amount of “philosophical” and story-telling content on social media. Common traits are a calm voice, soothing music, calm pictures and a discussion of some topic of self-improvement, or love, or the world and our place in it. The algorithms have noticed that I sometimes enjoy this content.
Some of this type of content has clearly AI-generated elements, for example using the same voice or images that are slightly off. So I wondered how hard it would be to create similar content in a 100% automated manner.
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/victorqribeiro/TinyJS
作者: atum47
热门程度: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.degengen.com/
作者: bsmith15x
Please provide the text you would like me to translate.: HN,
One month of grinding and I’m excited to share degengen.com with you all.
degengen is all about making a more fun, social trading experience that’s community first via generative trading pages and generative chats.
I wanted a DEXTools that maximizes fun and community.
How It Works:
Generative Trading Pages: Enter a token name or address, and degengen creates a unique and novel trading page filled with surprises—a generative chat, a trading chart, and other goodies.
Make Changes Instantly: As the page creator, you can make changes using generative AI. Click “make change,” describe your desired adjustments, and the AI handles it. You’ll need to be connected to your wallet or logged in before generating a page to make changes, as we associate your public key or login with the page created.
Community Engagement: Pages with the highest engagement get automatically linked to the token on the site, promoting community interaction on that page. Anyone can create a new page at any time by entering the token name or address. If a new page gains higher engagement later, it becomes the primary linked page.
Quick Generation: It takes about 30 seconds to generate a page and apply any changes.
Generative Chat: Each page features a generative chat component powered by an LLM, enhancing chats with unpredictable and fun interactions—a true degen experience.
I hope to iterate on this based on your feedback over the next days and weeks.
Happy trenching!
人气: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://zkarimi.com/drunk-tac-toe/
作者: zknowledge
Please provide the text that you would like me to translate.: Wanted to try out Cursor and was inspired by a recent podcast by Greg Isenberg/Jason Fried to make “weird” tech experiences.
Fun little
受欢迎程度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.youtube.com/watch?v=rj9W1_f46RM
作者: ivo_ovcharov
Popularity: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.youtube.com/watch?v=KJWwXvwjFTA
作者: johnwheeler
It seems like you haven’t provided any specific text for me to translate. Please share the text you’d like me to translate, and I’ll be happy to assist you!: Hello HN, I created a browser extension that records your screen and then sends keyframes over to the GPT Vision API for annotation.
The use case for my software is creating interactive product demos.
Here is my app giving a demo of itself (a milestone I am extremely proud of!):
https://www.interactivedemo.ai/d/APRNDj9hoONXXDu
In the demo, you can see how I’m extracting key frames from the screen recording and sending them over to the LLM with various annotations. I use AWS Lambda with FFMpeg layers for that.
For the keyframes, I draw a red dot on the cursor using Python Imaging Library (PIL) and I also draw sequence and timestamp information under the frames. I have a prompt I’ve been tuning for a while and it’s not perfect but, it still saves a ton of time and has great results.
The system prompt is:
“Generate brief, action-oriented web interaction descriptions. Use varied verbs, focus on direct results, and leverage provided context. Pay close attention to both original and scaled coordinates.”
but the user prompt is my secret sauce ;-)
I am launching it on Product Hunt in a few days here:
https://www.producthunt.com/posts/interactivedemo-ai
I created InteractiveDemo.ai because I like how Screen Studio feels, but it is Desktop Mac only, and it doesn’t have interactive features. Also, I like the ability to create my own A.I. features on top of interactive demos and just the space in general because I’ve been developing and showing off software for 24 years. It’s a natural fit for me.
Check it out at https://www.InteractiveDemo.ai
I appreciate your support and am happy to answer any questions HN has.
流行度: 2 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/LarsDu/DiffuMon
作者: LarsDu88
Please provide the text you would like me to translate.: I wanted to start getting into paper reproduction, so I created an implementation of Ho et al 2020 - the basic diffusion model that showed diffusion is a viable technique for image generation.
I hope this implementation is a bit simpler than others, and certainly easier to install/reproduce than other implementations for educational purposes.
流行度: 4 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/Page-Replica/page-replica
作者: nirvanist
Popularity: 3 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
作者: gaieges
Please provide the text you would like me to translate.: I’ve been inundated with political ads, news and commentary from all angles and it’s exhausting. I’ve wanted just to hear about interesting topics about tech, and other areas of interest- especially in my podcasts while taking the dog for a walk.
So I built a simple tool that allows you to determine news articles that goes into each podcast. You can select a few topics you’re interested in, and get a new podcast daily consisting only of those topics.
This is still early on so feedback is welcome. Let me know what you think!
人气: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://eveeve.org/tomolld/page/fa36c1d5-8c24-4e86-87f1-2826e1367eb0
作者: tomolld
人气: 1 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://loomina.net/
作者: kindred
Please provide the text you would like me to translate.: For years I’ve been thinking about how challenging it is to learn new subjects on your own. There are plenty of resources, but they often lack personalized guidance, and one-to-one mentorship doesn’t scale to 7 billion people.
That’s why we’re building Loomina, a free open beta for our AI-driven learning platform where you can design your own mentors, lessons, and quizzes on any subject.
The goal is to make learning more accessible and tailored to individual needs, whether you’re casually curious or pursuing advanced studies.
We’d love to hear your thoughts!
受欢迎程度: 3 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: #
作者: sirobg
It seems like you provided only the word “Description.” Please provide the text you would like translated.: Hey HN!
I just published https://meet.hn, a map to find hackers in your city.
How it works?
Demo of the signup process: https://x.com/meet_hn/status/1834918518904746329
1. Fill the form: username, city+country
2. Copy the text generated in the box below the form, and paste it in your HN description.
3. Click “Add me on the map”
Optionnaly (it’s recommended!) you can add links to your socials as well as some tags to showcase your interests.
Why does it exist?
I created this because, despite its harsh reputation on the internet, I love the HN community. I have fewer than a handful of friends who are as curious and eager to think and reflect as the people on HN. Also, the city I currently live in is more focused on industry than on technology and entrepreneurship, which are core to HN.
This led me to want to meet the HN community IRL.
After trying site:news.ycombinator.com/user toulouse
on Google and getting only one result, I decided to create meet.hn.
My first goal with this is to meet at least one HN member in my city: Toulouse, France. If you are ever in the area, hit me up! I’m sirobg at https://meet.hn/city/fr-Toulouse
Additional details:
- meet.hn has a twitter page: https://x.com/meet_hn. If you meet IRL thanks to meet.hn, don’t hesitate to tag it with a picture, it would mean the world to me.
- the code is open source: https://github.com/borisghidaglia/meet-hn
- meet.hn integrates with https://at.hn/ from @padolsey (https://padolsey.at.hn/), registered on meet.hn at https://meet.hn/city/cn-Beijing
Finally, many thanks to these people for their help and/or feedbacks! Ordered alphabetically:
- https://x.com/JulienDuquesne1
- https://www.linkedin.com/in/lbasseto/
I hope you will enjoy this! Please share any feedback in the comments.
受欢迎程度: 623 points | 297 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/thomastschurtschenthaler/electrico
作者: thomastsch
受欢迎程度: 7 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.soundai.studio/
作者: meth990
Sure, I can help with that. Please provide the text you would like me to translate.: I have created this advanced tool to generate sound effects with Ai. hope you like it and I appreciate the feedback
子人気: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://speech.fish.audio/
作者: techFFF
It seems that your request is incomplete. Could you please provide the text you would like me to translate?: Fish Speech is an innovative Text-to-Speech (TTS) open source tool that offers a high degree of customization and flexibility to meet users’ personalized voice needs.
受欢迎程度: 6 points | 1 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://commitbuddy.webflow.io/
作者: ZaakirDev
Please provide the text you would like to have translated.: Commit Buddy sends daily GitHub streak reports and personalized motivation straight to your Discord inbox! Track your contributions, stay consistent, and hit your coding goals with ease. All for free. Level up your GitHub game today!
人气: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://invoicedataextraction.com/
作者: davidh_js
Please provide the text you would like me to translate.: Hi HN, I’ve built a SaaS to solve a data entry task that I have often had as a business owner - to be able to extract key invoice data from batches of invoice files for financial record keeping.
From my experience GPT-4o now outperforms traditional OCR for extracting text from documents, plus the LLM’s reasoning ability means that specific data can be extracted and formats can be converted as desired. Traditional OCR services generally extract all text in the document and of course they extract it as-is without the ability to convert dates etc. Accounting software usually expects imported data to be in a specific format.
The tool can extract data from batches of mixed invoice types (PDF, Word, JPG, PNG) which is particularly useful for ‘bricks and mortar’ businesses who often have mixed format invoices such as scanned documents or photos of receipts. The data is extracted to a spreadsheet with columns that the user defines ready for the user’s workflow or for importing into their accounting software.
The tool optimizes the document contents for best LLM understanding - which isn’t necessarily what happens when you upload the documents to ChatGPT for example.
I’ve tried to make the software as easy to use as possible, so hopefully there isn’t a learning curve involved - it is just completing our template by using natural language to describe the data you need extracting. Again, with traditional (non LLM) OCR tools there is usually a learning curve involved in using the software, a long set-up process, and a rigid invoice format expected.
If there are any business owners, bookkeepers or accountants who think the tool might be useful for them then I’m extremely open to working with you as an early user to onboard you with additional free credits so you can test out the software.
I’ve tried to keep this brief - it would be great to hear feedback or hear from anyone who thinks this might be useful for them!
Best regards, David.
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://www.giz.ai/openai-o1-for-free/
作者: ktkim
受欢迎程度: 4 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
作者: Navkun
It seems like you’ve provided a single word, “Description,” without any additional context or content to translate. Could you please provide the full text or more details that you would like translated?: I’m sure you all saw the debate a few days ago, alongside all the tech influencoors giving their mid-takes about politics.
Doesn’t it get tiring?
That’s why I built mindfirewall a chrome extension that uses AI to filter out tweets.
You’ll never have to see politics, war, or negativity on your timeline again.
In the future you’ll be shocked you even allowed this stuff into your brain in the first place.
Let me know what you think below, does it feel too much like censorship? would you use this?
流行度: 39 points | 90 comments
What do you think about this project? Share your thoughts in the comments!
作者: wolvgvng
It seems like you’ve only provided the word “Description.” Could you please provide a longer text or context that you would like translated into English?: Hi Hackers!
TLDR: After switching my daily OS from Linux to MacOs, I really miss something like Gnome Extensions store.
There is an AppStore, but it is quite poor.
I love configuring and upgrading my system, so I created such store myself.
Hope you like it, I would love to hear your opinions!
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/ktmouk/minute
作者: ktmouk
流行度: 4 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://aigirl.sense-ocean.com
作者: ElkeQin
Please provide the text you would like me to translate.: One day, during a conversation with family and friends about internet safety, I realized a pressing need: as kids are getting access to the internet at younger ages, many parents are concerned about their children accidentally coming across inappropriate content, especially online pornography. However, the existing solutions are often not smart enough to prevent or dynamically identify these risks.
I understood that this isn’t just a technical issue, but a societal one. Parents are looking for a tool that leverages advanced technology, like AI, to protect their children in real time from harmful content. With this in mind, I set out to create a solution that not only blocks explicit content while browsing but also learns and improves its filtering capabilities through AI.
It took me several months of development, facing various challenges along the way. For instance, ensuring that the AI accurately identifies and blocks a wide range of explicit content while keeping the browsing experience smooth, and making the system adaptable to different user needs. After several iterations and improvements, I finally launched No Porn - AI Porn Blocker.
Key features of this product include:
I invite you to try it out and share your feedback, so we can continue to improve and refine the product!https://noporn.net
受欢迎程度: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
作者: artistaiden
人气: 1 points | 0 comments
What do you think about this project? Share your thoughts in the comments!
URL: https://github.com/threader/AltanOS/blob/main/src/strip_windows.ps1
作者: threaderr
受欢迎程度: 4 points | 4 comments
What do you think about this project? Share your thoughts in the comments!
Today’s Show HN roundup showcases a diverse range of innovative projects. From AI-powered tools to creative coding solutions, these projects reflect the dynamic nature of our tech community. Which project caught your attention the most? Let us know in the comments!
Tags: #ShowHN #TechInnovation #DeveloperProjects #AIApplications #Open Source Software