The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Open-source coding assistant with terminal access
Sweep is an AI coding assistant that reads your files and runs code in your terminal. It takes a list of files and instructions, and performs edits using GPT4. For example, you can tell Sweep to reference a.tsx to localize b.tsx.<p>We previously worked on Sweep as a bot that generated pull requests from GitHub issues. We learned that AI needs validation (like formatters and unit tests) to code properly. We tried setting up a code sandbox for each user but this didn't work well. We’re now relying on the prebuilt dev environment on their machine to avoid having to install dependencies.<p>LLM based pipelines are also error-prone. Our previous project was a pipeline that turns the issue into relevant files as context, relevant files to a generated plan of files to change, and then the generated plan to a series of code changes. It’s frustrating when one/all of these steps fail and you’re forced to start over. You can now intervene at each step, making the entire process more reliable.<p>Sweep is open source (licensed under AGPL) and runs entirely on your laptop. The only remote calls will be to OpenAI. We'd love to help you perform software chores like version upgrades, where you describe a set of changes to have Sweep apply over multiple files. You can install Sweep here with a one-line command: <a href="https://docs.sweep.dev/assistant">https://docs.sweep.dev/assistant</a>. We'd love to hear any feedback you have!
Show HN: SnapCode – a real Java IDE in the browser
Show HN: SnapCode – a real Java IDE in the browser
Show HN: Lookup the school district associated with a street address in the US
I wrote a tool in Python that finds the school district associated with any given street address in the United States.<p>Here’s how it works:<p>An address corresponds to a single point on the map. The U.S Census Bureau has a geocoder that converts an address to latitude and longitude coordinates.<p>School district boundaries can be represented as polygons on the map. The National Center for Education Statistics (NECS) has geographic data on school district boundaries.<p>Once we determine which polygon the point resides in, we know the school district.
Show HN: Lookup the school district associated with a street address in the US
I wrote a tool in Python that finds the school district associated with any given street address in the United States.<p>Here’s how it works:<p>An address corresponds to a single point on the map. The U.S Census Bureau has a geocoder that converts an address to latitude and longitude coordinates.<p>School district boundaries can be represented as polygons on the map. The National Center for Education Statistics (NECS) has geographic data on school district boundaries.<p>Once we determine which polygon the point resides in, we know the school district.
Show HN: Lookup the school district associated with a street address in the US
I wrote a tool in Python that finds the school district associated with any given street address in the United States.<p>Here’s how it works:<p>An address corresponds to a single point on the map. The U.S Census Bureau has a geocoder that converts an address to latitude and longitude coordinates.<p>School district boundaries can be represented as polygons on the map. The National Center for Education Statistics (NECS) has geographic data on school district boundaries.<p>Once we determine which polygon the point resides in, we know the school district.
Show HN: Daily price tracking for Trader Joe's
Show HN: Daily price tracking for Trader Joe's
Show HN: Daily price tracking for Trader Joe's
Show HN: Daily price tracking for Trader Joe's
Show HN: YTPics – Download pictures from YouTube videos
Lack of yt-dlp+ffmpeg and screenshots' limited size on my mobile phone prompted me to build a simple tool to download pictures from YouTube videos. Check it out. hope you guys find it useful
Show HN: YTPics – Download pictures from YouTube videos
Lack of yt-dlp+ffmpeg and screenshots' limited size on my mobile phone prompted me to build a simple tool to download pictures from YouTube videos. Check it out. hope you guys find it useful
Show HN: YTPics – Download pictures from YouTube videos
Lack of yt-dlp+ffmpeg and screenshots' limited size on my mobile phone prompted me to build a simple tool to download pictures from YouTube videos. Check it out. hope you guys find it useful
Show HN: Improve cognitive focus in 1 minute
Staring at something for 30-90 seconds has been proven to improve & boost mental focus on subsequent tasks (from Andrew Huberman - <a href="https://youtu.be/CrtR12PBKb0?t=3367" rel="nofollow">https://youtu.be/CrtR12PBKb0?t=3367</a>
).<p>So I made something simple you can look at (and simultaneously meditate) for 1 minute to improve focus for your next task :) Let me know if it works for you
Show HN: Improve cognitive focus in 1 minute
Staring at something for 30-90 seconds has been proven to improve & boost mental focus on subsequent tasks (from Andrew Huberman - <a href="https://youtu.be/CrtR12PBKb0?t=3367" rel="nofollow">https://youtu.be/CrtR12PBKb0?t=3367</a>
).<p>So I made something simple you can look at (and simultaneously meditate) for 1 minute to improve focus for your next task :) Let me know if it works for you
Show HN: Improve cognitive focus in 1 minute
Staring at something for 30-90 seconds has been proven to improve & boost mental focus on subsequent tasks (from Andrew Huberman - <a href="https://youtu.be/CrtR12PBKb0?t=3367" rel="nofollow">https://youtu.be/CrtR12PBKb0?t=3367</a>
).<p>So I made something simple you can look at (and simultaneously meditate) for 1 minute to improve focus for your next task :) Let me know if it works for you
Show HN: Improve cognitive focus in 1 minute
Staring at something for 30-90 seconds has been proven to improve & boost mental focus on subsequent tasks (from Andrew Huberman - <a href="https://youtu.be/CrtR12PBKb0?t=3367" rel="nofollow">https://youtu.be/CrtR12PBKb0?t=3367</a>
).<p>So I made something simple you can look at (and simultaneously meditate) for 1 minute to improve focus for your next task :) Let me know if it works for you
Show HN: Improve cognitive focus in 1 minute
Staring at something for 30-90 seconds has been proven to improve & boost mental focus on subsequent tasks (from Andrew Huberman - <a href="https://youtu.be/CrtR12PBKb0?t=3367" rel="nofollow">https://youtu.be/CrtR12PBKb0?t=3367</a>
).<p>So I made something simple you can look at (and simultaneously meditate) for 1 minute to improve focus for your next task :) Let me know if it works for you
Show HN: ReadToMe (iOS) turns paper books into audio
I'm launching something that started as a side project publicly today: ReadToMe, which is an iPhone app that turns paper books and other printed text into audio.<p>Originally this was a Christmas present for my fiancée, who loves books but has an eye problem that makes it hard for her to read more than a few pages at a time. She mostly listens to audiobooks while following along with the paper book, but some books aren't available in audiobook or even e-book form, and all of the existing apps we tried were surprisingly bad at scanning paper books into audio — they make lots of mistakes, include footnotes and page numbers, etc., in a way that really degrades the experience.<p>Being an AI-oriented engineer by training, I had a crack at solving the problem myself, and was pleasantly surprised at how well the proof of concept worked. I then had some time free while shutting down my previous company (Mezli, YC W21), during which I polished up the app to the point you see it at now.<p>The way it works:<p>On the front end, it's a SwiftUI app (mostly written by ChatGPT!) that consists mostly of a document scanner (VNDocumentCameraViewController) and a custom-built audio player.<p>The back end is more complex — book photos are first sent to an OCR API, then some custom code I wrote does a first pass at stitching together and correcting the results. Then, the corrected OCR results are sent to GPT-3.5-turbo for further post-processing and re-stitching together, and finally to a text-to-speech API for conversion to audio.<p>The hardest part of this process was actually getting the GPT calls right — I ended up writing a custom LLM eval framework for making sure the LLM wasn't making edits relative to the true text of the book.<p>A few issues remain, which I'll work on fixing if the app gets a significant amount of traction, including:<p>1) It can take multiple minutes to get audio back from a scan, especially if it's on the longer side (10+ pages). I'll be able to bring this down by spinning up dedicated servers for the OCR and TTS back-end.<p>2) The LLM sometimes does TOO good of a job at correcting "mistakes" in book text. This issue crops up particularly often when an author deliberately uses improper grammar, e.g. in dialogue.<p>The app is priced at $9.99/month for up to 250 pages/month right now, which I estimate will just about cover the costs of API calls. I'll be bringing the price point down as the pricing of the required AI APIs comes down. There's also a 3-day free trial if you want to try it out.<p>If you do find this useful, or know somebody who might, I'd appreciate you giving it a try or letting them know! And please let me know if you have any feedback, including issues or feature requests.
Show HN: Logdy.dev – web based log viewer UI for local development environments