Show HN: Stock Market Today https://ift.tt/aVyALQD

Show HN: Stock Market Today https://ift.tt/sxMoJGm September 1, 2023 at 03:42AM

Show HN: Name Checker – check your project name accross many sites https://ift.tt/UokeGaF

Show HN: Name Checker – check your project name accross many sites https://ift.tt/D7v85C9 September 1, 2023 at 08:35AM

Show HN: Travel search engine calculating results in single digit ms https://ift.tt/ekHDfZz

Show HN: Travel search engine calculating results in single digit ms https://ift.tt/tIykZzX September 1, 2023 at 04:48AM

Show HN: NumberTabs, A Notes App for your calculations https://ift.tt/oczaBKQ

Show HN: NumberTabs, A Notes App for your calculations A Notes App for your daily calculations. This App provides a simple way to manage and note your day-to-day calculations easier and faster. https://ift.tt/zcKyuhM August 31, 2023 at 09:06PM

Show HN: Squabblr – A Twitter/Reddit hybrid platform https://ift.tt/kitI1em

Show HN: Squabblr – A Twitter/Reddit hybrid platform Hey guys, I made a post about this about a week ago and was told to create a Show HN post. So here we are! Squabblr is a hybrid that takes Twitter style posting and combines it with Reddit style commenting. It came up from a personal want where I liked using Twitter to see what people I'm interested in are up to, but found that the reply system left a lot to be desired. It's very hard to have or follow conversations with their UI. While Reddit provided a great commenting system but didn't support following people very well (or had much usage of it at all). So I decided to create Squabblr. You can "tweet" random blurbs or have in-depth conversations in a single unified platform. You can follow people, and you can also have Reddit style communities for whatever niche subject you find interest in. If you find any interest in it, check it out here! https://squabblr.com Tech stack: - Laravel - Vue.js - MySQL - DigitalOcean Appreciate your time! https://squabblr.co September 1, 2023 at 01:26AM

Show HN: Vanity Git commit hash generator https://ift.tt/V8D1I3f

Show HN: Vanity Git commit hash generator Hi HN! This is just a fun little tool I made after I got nerdsniped by noticing that one of my commits naturally started with "fae". I thought that was cute, so I looked up existing tools that make vanity commit hashes, but none of them seemed great to me (and none supporting signing commits). I learned a fair deal about how git actually stores commits while making this, and I think I came up with a novel way to generate a vanity hash: adding an extra header to the commit file. This was just a quick project to satisfy my curiosity, but I thought you all might find it neat. Notice that all the commits in that repo start with "fae0"! - Anna https://ift.tt/myYRehv August 31, 2023 at 02:13PM

Show HN: Tiny Dream – Header Only, Embedded Stable Diffusion C++ Library https://ift.tt/5Urb6CL

Show HN: Tiny Dream – Header Only, Embedded Stable Diffusion C++ Library https://ift.tt/Cw2qvmU August 30, 2023 at 10:16PM

Show HN: I automated 1/2 of my typing https://ift.tt/5bJNcaf

Show HN: I automated 1/2 of my typing I've been using this for about a year now - I parsed 6 months of my messages on slack and found the most common phrases I use and generated keyboard shortcuts for them. https://ift.tt/Mdjci1n August 31, 2023 at 01:40AM

Show HN: CLI Mate: autogenerate CLIs from Golang structs / functions https://ift.tt/nGU3yK9

Show HN: CLI Mate: autogenerate CLIs from Golang structs / functions With support for nested subcommands, global / local flags, help generation from godocs, typo suggestions, shell completion and more. Inspired by python-fire and powered by Cobra. https://ift.tt/8A6kDRU August 30, 2023 at 08:40PM

Show HN: How to Notebooks for computer vision models and techniques https://ift.tt/qJ19Exz

Show HN: How to Notebooks for computer vision models and techniques https://ift.tt/W6smvOi August 30, 2023 at 06:17PM

Show HN: Abookmark – advanced bookmark and tab/session manager https://ift.tt/UKvVt4O

Show HN: Abookmark – advanced bookmark and tab/session manager Abookmark is a chrome extension. It uses the native bookmarks as database. main features: - Labels/Tags. - Sticky notes in web pages. - Trash/Recycle. - Tab managments. (store & restore tabs/sessions.) - Sailing. (update saved bookmarks automatically while surfing) - Advanced bookmark bar (spread view & top bar) - Data text editor. (edit bookmarks in your favorite text editor) - Import selected bookmarks from a file. - Monthly backup. - Recent bookmarks. - Link hint. (vi-like keyboard) In Abookmark a bookmark is a sleeping tab and a tab is a living bookmark. The two can be converted into each other. Please backup your bookmarks before you try it. https://ift.tt/GjHKcTq August 30, 2023 at 06:35AM

Show HN: Hugo and Nebula Award Short Stories https://ift.tt/13MqWcf

Show HN: Hugo and Nebula Award Short Stories https://ift.tt/EYvtP6p August 30, 2023 at 04:38AM

Show HN: Query your database using plain English on premise https://ift.tt/aLtbiE2

Show HN: Query your database using plain English on premise Hi folks, My friend Sami and I recently built Vizly, a Mac application that allows anyone to query their databases using plain English. Vizly is built on Llama 2, llama.cpp, and runs fully on-premise. We are running two Llama models, one for natural language to SQL translation, and another that uses the results from the SQL to render visualizations. That means there are no external APIs and all the AI models are running locally on your MacBook. We tried to make Vizly very easy to share as well. Every Vizly instance creates a share link that can be accessed by anyone on the same network as you. Just send the share link to anyone on the same network and they will be immediately able to run AI-powered queries, hosted from your device. Vizly previously used to be a hosted solution for querying CSVs and now we are on-premise specifically focussed on databases. Would love if you could try it out and give us any feedback! https://www.vizly.fyi/ August 30, 2023 at 06:40AM

Show HN: Langfuse – Open-source observability and analytics for LLM apps https://ift.tt/qm0DZln

Show HN: Langfuse – Open-source observability and analytics for LLM apps Hi HN! Langfuse is OSS observability and analytics for LLM applications (repo: https://ift.tt/NmCdRjl , 2 min demo: https://ift.tt/WrvsLay , try it yourself: https://ift.tt/Jm6Bosd ) Langfuse makes capturing and viewing LLM calls (execution traces) a breeze. On top of this data, you can analyze the quality, cost and latency of LLM apps. When GPT-4 dropped, we started building LLM apps – a lot of them! [1, 2] But they all suffered from the same issue: it’s hard to assure quality in 100% of cases and even to have a clear view of user behavior. Initially, we logged all prompts/completions to our production database to understand what works and what doesn’t. We soon realized we needed more context, more data and better analytics to sustainably improve our apps. So we started building a homegrown tool. Our first task was to track and view what is going on in production: what user input is provided, how prompt templates or vector db requests work, and which steps of an LLM chain fail. We built async SDKs and a slick frontend to render chains in a nested way. It’s a good way to look at LLM logic ‘natively’. Then we added some basic analytics to understand token usage and quality over time for the entire project or single users (pre-built dashboards). Under the hood, we use the T3 stack (Typescript, NextJs, Prisma, tRPC, Tailwind, NextAuth), which allows us to move fast + it means it's easy to contribute to our repo. The SDKs are heavily influenced by the design of the PostHog SDKs [3] for stable implementations of async network requests. It was a surprisingly inconvenient experience to convert OpenAPI specs to boilerplate Python code and we ended up using Fern [4] here. We’re fans of Tailwind + shadcn/ui + tremor.so for speed and flexibility in building tables and dashboards fast. Our SDKs run fully asynchronously and make network requests in the background. We did our best to reduce any impact on application performance to a minimum. We never block the main execution path. We've made two engineering decisions we've felt uncertain about: to use a Postgres database and Looker Studio for the analytics MVP. Supabase performs well at our scale and integrates seamlessly into our tech stack. We will need to move to an OLAP database soon and are debating if we need to start batching ingestion and if we can keep using Vercel. Any experience you could share would be helpful! Integrating Looker Studio got us to first analytics charts in half a day. As it is not open-source and does not work with our UI/UX, we are looking to switch it out for an OSS solution to flexibly generate charts and dashboards. We’ve had a look at Lightdash and would be happy to hear your thoughts. We’re borrowing our OSS business model from Posthog/Supabase who make it easy to self-host with features reserved for enterprise (no plans yet) and a paid version for managed cloud service. Right now all of our code is available under a permissive license (MIT). Next, we’re going deep on analytics. For quality specifically, we will build out model-based evaluations and labeling to be able to cluster traces by scores and use cases. Looking forward to hearing your thoughts and discussion – we’ll be in the comments. Thanks! [1] https://ift.tt/AZazgMs [2] https://ift.tt/zckCOwJ [3] https://ift.tt/bm03Zdz [4] https://ift.tt/QWGLc8K https://ift.tt/NmCdRjl August 29, 2023 at 11:14PM

Show HN: Open-source tool to limit AWS spendings https://ift.tt/KZdCAnR

Show HN: Open-source tool to limit AWS spendings https://ift.tt/NShY7FG August 29, 2023 at 10:54PM

Show HN: Mu – A Micro App Platform https://ift.tt/JNuXt1M

Show HN: Mu – A Micro App Platform Hey all Sharing a new piece of work I've been doing with a friend. Mu is a new micro web app platform which enables building and sharing apps instantly with storage, auth and payments built in. Apps are single file, built in the browser and rendered as an iframe. They're "micro" because they're quite literally tiny single purpose utilities like a hackernews reader or old school guest book. It's mostly at this point something that scratches a personal itch. Making app development super simple and lightweight. Sort of like living GitHub gists. And trying to build a simpler, cleaner place to consume the web. Right now nothing more than a cool hack I'm sharing. Feedback obviously welcome. Cheers Asim https://mu.app August 29, 2023 at 06:42PM

Show HN: Advanced Tab Manager for Firefox https://ift.tt/OQDrRFb

Show HN: Advanced Tab Manager for Firefox https://ift.tt/zO4mvWM August 29, 2023 at 06:20PM

Show HN: Toybox – A Laravel TALL starter kit for solopreneurs https://ift.tt/SA0Ya1G

Show HN: Toybox – A Laravel TALL starter kit for solopreneurs Hey peeps! Here's a project I've been working on for the last two months. It initially started as trying to be a simplified boilerplate for Laravel, but I think it's gone a bit beyond that. With recent tooling releases in the Laravel ecosystem, there's a ton of exciting tools to work with, but it's either annoying to set it all up every time, or it's difficult to try and gather it all up for every piece you'll need for your SaaS. To that end, Toybox attempts to collate what is in my opinion the best of modern Laravel, and while being simple to start, run and launch with. This is how I also came up with the name - pick and choose all your favourite Laravel toys and see how quickly you can build products with it. I've never been a fan of Docker and similar tools. While I see their value, I've generally not had a good experience and it always felt like a waste of my time trying to debug infrastructure instead of writing application code. So on that front Toybox goes back to basics - it targets only one stack, and is made to be able to initialise its repository, provision the server it is currently on, and deploy itself from your local machine, all with Bash scripts. Lastly, I tried to include guidance and support for scaling beyond an MVP and Bash scripts: The README includes tons of recommendations for various services & tools for all manner of things you need for your SaaS. https://ift.tt/qgkRoTz August 29, 2023 at 03:56PM

Show HN: Speak in Gaelic to ChatGPT https://ift.tt/Ez6ZBYw

Show HN: Speak in Gaelic to ChatGPT https://ift.tt/6DLohX7 August 29, 2023 at 06:40AM

Show HN: MuscleWiki Advanced Bodymap – A More Granular Exercise Finder https://ift.tt/vNyPI59

Show HN: MuscleWiki Advanced Bodymap – A More Granular Exercise Finder We are currently working on moving our site over to a react front end and adding more features to the site. I wanted to highlight one we are quite proud of - The advanced bodymap. Click the advanced button and get specific exercises that work that muscle. We are hoping to have an even bigger breakdown in the future when we build our "recovery" section of the site. Happy to answer any questions and take feature requests. https://ift.tt/1aSOrZI August 29, 2023 at 12:31AM

Show HN: Deploying computer vision apps with Docker and Pipeless https://ift.tt/8Sx3sHy

Show HN: Deploying computer vision apps with Docker and Pipeless https://ift.tt/b8cnP5k August 28, 2023 at 10:06PM

Show HN: Mail Organizer for Gmail https://ift.tt/XOVLMvJ

Show HN: Mail Organizer for Gmail This Google Apps Script labels emails accoding to the address the email was sent to. For example, you own the domain name "example.com", and you set up an email forwarding service such as Forward Email or ImprovMX to relay all emails sent to "*@relay.example.com" to your Gmail account. The script will label your emails according to a set of rules. For example: - "hello@relay.example.com" will be labeled "hello" - "hello-world@relay.example.com" will be labeled "hello" and "world" - "hello.world@relay.example.com" will be labeled "hello/world" ("world" as a sublabel of "hello") - "hello.world-yo.wassup@relay.example.com" will be labeled "hello/world" and "yo/wassup" https://ift.tt/XmjKhnz August 28, 2023 at 01:05PM

Show HN: FlagPalette – Flag Color Codes https://ift.tt/82ST0N3

Show HN: FlagPalette – Flag Color Codes https://ift.tt/N1ms2nL August 28, 2023 at 03:16PM

Show HN: MoodMinder – Swift Anger Regulation for Better Emotional Well-Being https://ift.tt/4yx0dCX

Show HN: MoodMinder – Swift Anger Regulation for Better Emotional Well-Being Hey Hacker News community! We're excited to showcase MoodMinder, a mental health app MVP that empowers individuals to swiftly regulate anger and enhance emotional well-being. MoodMinder was born out of a desire to provide quick anger regulation solutions for busy individuals. Unique Features: Rapid Mood Identification: Identify anger triggers and tension levels swiftly. Instant Personalized meditations: Receive tailored meditations for immediate anger control. Cognitive Reappraisal: Shift perspectives to defuse triggers in real-time. Quick Interactive Games: Engage in games designed for anger regulation in just minutes. As an MVP, we're seeking insights from the Hacker News community to shape our app's development. Your feedback is pivotal. Thank you for being part of our journey! https://ift.tt/CPHKeXF August 27, 2023 at 11:12PM

Show HN: Hermes – SMM backdoor and client for usermode privilege escalation https://ift.tt/4TM5osd

Show HN: Hermes – SMM backdoor and client for usermode privilege escalation Hermes is an open source system management mode backdoor which allows a user mode application to elevate its own privileges and interact with memory without any direct access at smm level. https://ift.tt/wNnckru August 27, 2023 at 11:56PM

Show HN: RISC-V Linux terminal emulated via WASM https://ift.tt/gshLOxH

Show HN: RISC-V Linux terminal emulated via WASM Weekend creation: A Linux terminal on top of a RISC-V emulator running in the browser via WebAssembly, powered by the Cartesi Machine. Check cool commands to experiment in the project page https://ift.tt/eiqwmVL https://ift.tt/XCVoUFg August 28, 2023 at 02:51AM

Show HN: Bicycle – A Database Tool (Rust, gRPC, RocksDB) https://ift.tt/JKq4mvE

Show HN: Bicycle – A Database Tool (Rust, gRPC, RocksDB) https://ift.tt/GnqMH1L August 27, 2023 at 11:54PM

Show HN: Customizable terminal UI for monitoring weather, app uptime, and more https://ift.tt/F1SKWZn

Show HN: Customizable terminal UI for monitoring weather, app uptime, and more https://ift.tt/yLJUcSi August 27, 2023 at 04:20PM

Show HN: Investor Radar, the Ultimate Database of Investors for Your Startup https://ift.tt/VvR5aAd

Show HN: Investor Radar, the Ultimate Database of Investors for Your Startup https://ift.tt/zgBxdjY August 27, 2023 at 05:25AM

Show HN: Dumbar, a not so smart menubar app https://ift.tt/NbDtdP1

Show HN: Dumbar, a not so smart menubar app I created this to fill a need, accessing those silly LLMs from the menu bar instead of a web browser or command line. It relies 100% on Ollama, but gives you an easy way to make queries against multiple models, and provides a few sample modelfiles for you. open source, of course. https://ift.tt/KY41jFn to skip the blog post and go straight to the code and release. https://jerrysv.xyz/blog/dumbar.html August 27, 2023 at 02:57AM

Show HN: TRS-GPT - ChatGPT client/server for the TRS-80 https://ift.tt/Gpqx92Y

Show HN: TRS-GPT - ChatGPT client/server for the TRS-80 Hi there HN community. I'm excited to show my personal project -- an open-source code and hardware approach that connects my 1980's TRS-80 Model III computer to an OpenAI server. The TRS-80 can hold a chat session with OpenAI, and it's all very retro feeling. There were challenges along the way, as the approach to interfacing between ancient hardware and modern software interface wasn't immediately available. Please see https://ift.tt/hKYq1GR for all the details, and let me know if you have any ideas for improvements. For example, adding support for voice. https://ift.tt/HiE1ABM August 27, 2023 at 02:27AM

Show HN: Going into Freshman Year, Figured I Should Build an Interpreter ¯\(ツ)/¯ https://ift.tt/vG6pVqE

Show HN: Going into Freshman Year, Figured I Should Build an Interpreter ¯\(ツ)/¯ Hi all! I'm going into my freshman year, and figured that the best way to prepare for the intro to programming Racket course would be to implement my own garbage-collected, dynamically typed, functional programming language in C ;) Anyways... here's the repo: https://ift.tt/RmJonht I started learning C over the summer, so I still have a whole lot to learn... Any feedback would be greatly appreciated! :D August 27, 2023 at 12:28AM

Show HN: Idae, a PEP 723 Implementation https://ift.tt/QyY51Tx

Show HN: Idae, a PEP 723 Implementation https://ift.tt/hIPUcvH August 27, 2023 at 12:49AM

Show HN: Email Enricher, a Free, Offline Clearbit Alternative https://ift.tt/3CgeS90

Show HN: Email Enricher, a Free, Offline Clearbit Alternative At my prior employer, we got Slack alerts for big company sign-ups I wanted the same for my new startup ( https://fillout.com ) but quickly found that Clearbit would cost us $7,000 / mo... Instead, I made this free npm package `email-enricher` the returns if an email is likely from a Fortune 1000 company Hope it's useful to someone else! https://ift.tt/qYz2frU August 26, 2023 at 04:21AM

Show HN: Display primary keys the way humans and developers prefer https://ift.tt/EXfvBch

Show HN: Display primary keys the way humans and developers prefer https://ift.tt/vMTLEH8 August 26, 2023 at 04:50PM

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas https://ift.tt/kBrMyR3

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas AhaApple. AI Idea Generator. One click, Many Creative and Novel Ideas. Leveraging AI, many brainstorming techniques, and many innovative techniques, AhaApple make it easy for you to gain more inspirations and ideas. https://ift.tt/SqgGiR0 August 26, 2023 at 11:52AM

Show HN: Full list of ChatGPT Plugins and stats https://ift.tt/SepPBm2

Show HN: Full list of ChatGPT Plugins and stats https://ift.tt/LZqHfz2 August 25, 2023 at 10:42PM

Show HN: Mail Memories – Export your email photos https://ift.tt/Y4EK0kF

Show HN: Mail Memories – Export your email photos Hey HN, I’m Carlos, the maker behind Mail Memories ( https://ift.tt/gN8CqEo ), a web app that helps you find and save photos from your (Gmail) email. The app connects with your email account, finds all the images you’ve received and shows them in a gallery where you can view and download the ones you want to save. I made this out of curiosity, just to see what pictures were in my account when I first signed up for Gmail 18 years ago. I ended up finding photos of my grandmother and other family members, and old friends and colleagues I’d completely forgotten about. I was surprised by what I found, I hope you will be too. Can’t wait to hear your thoughts. Demo: https://ift.tt/9G02g4m https://ift.tt/gN8CqEo August 26, 2023 at 02:12AM

Show HN: I’m a startup nerd, I spend roughly 10h a week researching trends https://ift.tt/tBjAEJO

Show HN: I’m a startup nerd, I spend roughly 10h a week researching trends https://ift.tt/RCE5M7h August 25, 2023 at 10:26PM

Show HN: Release AI – Talk to Your Infrastructure https://ift.tt/WYltrp3

Show HN: Release AI – Talk to Your Infrastructure Hello, Hacker News! I'm David, cofounder of Release (YCW20). Introducing Release AI, a tool designed to empower users with instant access to DevOps expertise, all without monopolizing the valuable time of our experts. Developed with the developer and engineer community in mind, Release AI takes the power of OpenAI's cutting-edge GPT-4 public LLM and augments it with DevOps knowledge. In its initial phase, Release AI offers "read-only" access to both AWS and Kubernetes. This means you can engage in insightful conversations with your AWS account and K8s infrastructure effortlessly. Looking ahead, our roadmap includes plans to integrate more tools for commonly used systems. This will enable you to automate an even broader array of your daily tasks. If you would like more info you can check-out our launch YC (it has more details, screen casts): https://ift.tt/seS98fC... Our quickstart guide: https://ift.tt/6ZIETUn Signup and use it: https://ift.tt/81zrSLt Please give it a try! We would love your feedback as we are enhancing Release AI, reach out to us with any feature requests or crazy ideas that Release AI could do for you. Feel free to email me at david@release.com or leave a comment, looking forward to chatting with you. Join the conversation in our Slack community and discover the future of DevOps with Release AI! https://ift.tt/Lq5KZub August 25, 2023 at 11:20PM

Show HN: Collie – A minimal RSS reader just for you https://ift.tt/RP1LuyV

Show HN: Collie – A minimal RSS reader just for you Collie is a minimal RSS feed reader application running on your desktop. With Collie, you can subscribe to multiple RSS/Atom feeds to organize your own news feed, receive a real-time notification when a new item is added to the subscribed feed, and save the items to read again or later. All you need is a local machine and the Internet. No virtual machine, no cloud infrastructures, no always-on database, and no account registration with privacy information required. I've been getting tech news from HackerNews, Lobsters, etc. on Twitter (It's X now, but I'll keep calling it Twitter anyway), but many of them have been terminated due to changes in Twitter's API policy. I went from place to place: Bluesky, Mastodon, Slack, and newsletter. However, I couldn't settle anywhere. The social media services such as Bluesky and Mastodon had too many unnecessary features as news feed. Slack RSS was good to get the news in real-time, but the notifications mixed with other workspaces overwhelmed me. The newsletters gave me a lot of high-quality information, but not in real-time. Then, I remembered Miniflux, the "minimalist and opinionated feed reader" that I had used past. This is the best option for my goal, but I had to pay for the hosted version or keep running docker machine on my local computer which did not have enough resources. Additionally, I didn't need a system that maintains multi-user sessions. Eventually, I had no choice but to create my own application, and that's why I made Collie, the minimal RSS reader just for me. https://ift.tt/oztKpTM August 25, 2023 at 12:28PM

Show HN: Convert Text, PDF, Docs, Scan or Image to Speech https://ift.tt/ZRFEKc7

Show HN: Convert Text, PDF, Docs, Scan or Image to Speech https://ift.tt/RuN8KJH August 25, 2023 at 12:43AM

Show HN: Shimmer – ADHD coaching for adults, now on web https://ift.tt/L8FC1UM

Show HN: Shimmer – ADHD coaching for adults, now on web Hi, I’m Chris, one of the co-founders of Shimmer. Last October, following my ADHD diagnosis, I launched Shimmer ( https://shimmer.care ), one-to-one ADHD Coaching for adults. Our HN launch was here: https://ift.tt/tE0VaMH . A quick recap before I dive into our new launch: Shimmer is an ADHD coaching service for adults. We took apart the traditionally expensive, inaccessible ADHD coaching offering ($300-600+/session) and redesigned it from first principles. You get matched with one of our expert ADHD coaches, meet weekly over video, and get supported throughout the week via text and with learning tools. This solution is special to me personally (and our community) because it doesn’t just give you “knowledge” or offer another “tool”—our coaches help you set realistic goals, take personalized steps towards it, and keep you accountable. Today we’re excited to launch our most-request feature: Web. Over the past 9 months, we learned (and iterated) a lot with our members and coaches. A few key challenges pointed to the need for a web version: (1) ADHD “object permanence” challenges (e.g. out of sight out of mind), we needed to be multi-platform so when you finish a task or goal or encounter a challenge, regardless of if you’re near your laptop or phone, you can check it off & ping your coach right away, (2) members used reflection modules (e.g. after each task, you’re prompted to reflect on what worked and didn’t work, and it informs your coach) more thoroughly than we originally anticipated, and web allows for deeper reflection and typing, (3) overarching coaching goals were often forgotten during the day-to-day, and the web makes it easier to use visual cues to keep goals top of mind for motivation, (4) many of our members struggle with phone addiction and driving members to the mobile app ended them up in Tiktok/IG, whereas the web app offers a focused environment to get in their “coaching zone”. Our new web app was designed alongside over 1,200 members, 22 coaches, countless hours of testing and iterating. We’re excited (but nervous!) to unveil this new version. If you have ADHD (or think you do), we’d love for you to check out our platform and give us critical feedback (or positive reinforcement!). It’s a super streamlined and ADHD-friendly signup process and in honor of our web launch and back to school/work, the first month is 30% off. Our pricing: $115/mo. for Essentials plan (15-min weekly sessions), $230/mo. for Standard plan (30-min weekly sessions), $345/mo. for Immersive plan (45-min weekly sessions); all plans additional 30% off first month, HSA/FSA-eligible. We know these prices are expensive for many people with ADHD and we’re committed to bringing costs down over time. It’s more affordable than what many people are paying for coaches, but the fact that we’re relying on humans, and not going the “we can automate all this with AI” route, puts a floor on how low the costs can drop. That said, here are some actions we’re taking to drive down costs for those who need it: (1) we offer needs-based scholarships and aim to have 5% of members on them at any time, (2) we often run fully sponsored scholarships with our partners—over 40 full ride scholarships and 100 group coaching spots have been disbursed alongside Asian Mental Health Project, government of Canada, and more, and (3) we have aligned our coaching model alongside Health & Wellness Coaching, which is expected to be reimbursed in 2024. If you have ideas or expertise here, please reach out to me directly at chris@shimmer.care. On behalf of our small but mighty & passionate Shimmer team, I’m excited for the Hacker News community to share your thoughts, feedback, and ideas. If you feel comfortable, I’d also love to hear your personal ADHD story and what has worked / hasn’t worked for you. Co-founders Christal & Vikram https://ift.tt/3CRueVM August 25, 2023 at 12:49AM

Show HN: Make a Website from Apple Notes https://ift.tt/W2ZnEyR

Show HN: Make a Website from Apple Notes Simple tool to create a blog or a website directly from Apple Notes. https://montaigne.io August 25, 2023 at 12:12AM

Show HN: Adapt Copilot to Your Goals https://ift.tt/2loNi3f

Show HN: Adapt Copilot to Your Goals https://ift.tt/aptRdG0 August 25, 2023 at 12:01AM

Show HN: Mertonon – Neural Organizational Management https://ift.tt/omeh1D4

Show HN: Mertonon – Neural Organizational Management Mertonon is a neural network budget for organizations. Neural network but not AI - Mertonon operationalizes your org's cost flow into a neural network and, based upon local human political decisions about the worth of cost nodes, stuck in weights which are determined by humans, allocates resources. Pre-alpha. Lots of work to do, but you can poke at it if you'd like. Authn, authz, hosting, an enterprise edition, double entry books, financial reporting, tax, currency, bom allocations, compliance, accounting controls, theory of value, theory of within-org inequality, theory of within-org class coming. https://ift.tt/FJKoXPQ August 24, 2023 at 11:49PM

Show HN: Chronos 12.0: Enhancing Monitoring with Grafana, Kubernetes, and More https://ift.tt/7HRTQaN

Show HN: Chronos 12.0: Enhancing Monitoring with Grafana, Kubernetes, and More Hey Hacker News Community! I wanted to share with you the latest release of Chronos 12.0, a powerful monitoring tool that's been upgraded to bring you even more features and capabilities. If you're into containerization or Kubernetes, this is something you won't want to miss. What's New in Chronos 12.0: * Grafana Charting and Visualizer: With the newly upgraded Grafana-based charting system, you can effortlessly visualize and compare diverse health metrics using various types of graphs. This includes Kubernetes environments and Docker containers, expanding the versatility of Chronos 12.0 as a monitoring tool. * Enhanced Prometheus and cAdvisor Integration: Our Prometheus and cAdvisor integration now covers nearly 50% more data points, including CPU, memory, and user interactions. This data aggregation brings enhanced accuracy and depth to docker health reports. * Immersive 3D Visualization for Kubernetes: Chronos 12.0 introduces an innovative 3D visualization that vividly portrays the Kubernetes cluster infrastructure. This visualization offers an intuitive depiction of interconnected relationships between core Kubernetes resources. * Increased Testing Coverage: Chronos 12.0 places a strong emphasis on testing, including unit tests, routing tests, and connection tests. This extensive testing regimen instills confidence in the reliability of Chronos 12.0, accurately diagnosing configuration issues. * Selenium-based End-to-End Testing: In addition to Jest unit and routing tests, Chronos 12.0 now includes Selenium-based end-to-end testing, enhancing testing capabilities for a more robust product. * Integrated CI/CD: Chronos 12.0 has taken a step towards Continuous Integration & Continuous Deployment (CI/CD) with automated GitHub Actions. This includes running testing suites and automatically updating dependencies for a smoother development process. * Improved Documentation: Our READMEs for configuring and operating Kubernetes and Docker Container examples have been extensively updated. Chronos 12.0 aims to provide step-by-step guidance through installations and operations, making it easier for developers to get started. How Can You Use Chronos? Implementing Chronos monitoring in your application is easy. Just check out our NPM package and follow the instructions in the README. Learn More: Chronos is an open-source project developed under the tech accelerator Open Source Labs. For more information, feel free to visit our website or check out the official Chronos GitHub page. We're excited about this release and would love to hear your thoughts and feedback. Let's enhance monitoring together with Chronos 12.0! https://ift.tt/bknLyaF August 24, 2023 at 09:41PM

Show HN: Open-source obsidian.md sync server https://ift.tt/mVfyRKc

Show HN: Open-source obsidian.md sync server https://ift.tt/O4TydRz Hello HN, I'm a recent high school graduate and can't afford $8 per month for the official sync service, so I tried my hand at replicating the server. It's still missing a few features, such as file recovery and history, but the basic sync is working. To the creators of Obsidian.md: I'm probably violating the TOS, and I'm sorry. I'll take down the repository if asked. It's not ready for production and is highly inefficient; Not competition, so I hope you'll be lenient. August 24, 2023 at 06:55PM

Show HN: OnePrompt – Personal Assistant ChatBot Using GPT https://ift.tt/ntIRLEX

Show HN: OnePrompt – Personal Assistant ChatBot Using GPT OnePrompt is an iOS application similar to ChatGPT, utilizing the OpenAI API. OnePrompt offers unique plugins of utilizing iOS native features through "function calling." It also allows users to create their own custom plugins. You can find more information about creating custom plugins for OnePrompt at https://ift.tt/qLGSpbE . https://ift.tt/5TtzxLY August 24, 2023 at 10:27AM

Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W https://ift.tt/XZ4weqD

Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W Hey HN community, I've recently embarked on a tinkering project that merges the versatility of the Badger 2040W with the practicality of an E-ink display. Inspired by the UK Rail departure boards, I've created an E-ink version that updates in real-time with departure information. Would love to hear your thoughts, suggestions, or similar projects you've come across! https://ift.tt/Tm413fb August 24, 2023 at 02:49AM

Show HN: I made danluu's blog easier to read https://ift.tt/aETQju8

Show HN: I made danluu's blog easier to read Hi, I'm Alex! I believe most of the knowledge is nowadays stored and hidden in personal blogs. I have a list of blogs that I read recurrently, and I have benefited myself a lot from this practice. One of the blogs that are usually recommended is the one by Dan Luu. Dan writes about a variety of topics in his blog, and I usually enjoy what he writes. But besides from the content Dan's blog stands out for the complete lack of CSS. IMHO this makes the content difficult to read (it's like reading text from a windows text editor). I believe more people will read and enjoy his blog if a pinch of CSS was added to the blog, so I've taken the liberty to enhance the reading experience. I wrote a script that periodically checks Dan's blog and publish the content in a static webpage (hosted using GitHub Pages). Regarding the CSS I just copied the CSS proposed in https://ift.tt/RdSWq1k and changed the font family. Give it a look and see what you think! Enjoy the improved readability. P.S. The code that does all this magic might not win any awards for beauty, but it gets the job done. If time permits, I "promise" to tidy it up in the future. Your understanding is appreciated! https://ift.tt/8kAliNQ August 24, 2023 at 05:18AM

Show HN: Dataherald AI – Natural Language to SQL Engine https://ift.tt/fbsXTHK

Show HN: Dataherald AI – Natural Language to SQL Engine Hi HN community. We are excited to open source Dataherald’s natural-language-to-SQL engine today ( https://ift.tt/vCocszf ). This engine allows you to set up an API from your structured database that can answer questions in plain English. GPT-4 class LLMs have gotten remarkably good at writing SQL. However, out-of-the-box LLMs and existing frameworks would not work with our own structured data at a necessary quality level. For example, given the question “what was the average rent in Los Angeles in May 2023?” a reasonable human would either assume the question is about Los Angeles, CA or would confirm the state with the question asker in a follow up. However, an LLM translates this to: select price from rent_prices where city=”Los Angeles” AND month=”05” AND year=”2023” This pulls data for Los Angeles, CA and Los Angeles, TX without getting columns to differentiate between the two. You can read more about the challenges of enterprise-level text-to-SQL in this blog post I wrote on the topic: https://ift.tt/3mQP2JL... Dataherald comes with “batteries-included.” It has best-in-class implementations of core components, including, but not limited to: a state of the art NL-to-SQL agent, an LLM-based SQL-accuracy evaluator. The architecture is modular, allowing these components to be easily replaced. It’s easy to set up and use with major data warehouses. There is a “Context Store” where information (NL2SQL examples, schemas and table descriptions) is used for the LLM prompts to make the engine get better with usage. And we even made it fast! This version allows you to easily connect to PG, Databricks, BigQuery or Snowflake and set up an API for semantic interactions with your structured data. You can then add business and data context that are used for few-shot prompting by the engine. The NL-to-SQL agent in this open source release was developed by our own Mohammadreza Pourreza, whose DIN-SQL algorithm is currently top of the Spider ( https://ift.tt/IrRCBk1 ) and Bird ( https://ift.tt/in7dU1Q ) NL 2 SQL benchmarks. This agent has outperformed the Langchain SQLAgent anywhere from 12%-250%.5x (depending on the provided context) in our own internal benchmarking while being only ~15s slower on average. Needless to say, this is an early release and the codebase is under swift development. We would love for you to try it out and give us your feedback! And if you are interested in contributing, we’d love to hear from you! https://ift.tt/vCocszf August 24, 2023 at 01:38AM

Show HN: Gentrace – evaluation and observability for generative AI https://ift.tt/4ospBlN

Show HN: Gentrace – evaluation and observability for generative AI Hi HN, Gentrace is our new evaluation and observability tool for generative AI (open beta). Generative pipelines are hard to evaluate because outputs are subjective. Lots of developers end up just doing “gut checks” on a few inputs before shipping changes, or they build up a spreadsheet of test cases that they manually run through the pipeline. Some companies outsource filling out the spreadsheet. However, in any of these cases, you end up with a very slow and expensive process for evaluation. At one point, we did this too. Gentrace is the result of a pivot; it was an internal tool we used to automatically grade new PRs as developers shipped changes to generative pipelines that other people thought might be useful. Gentrace makes pre-production testing of generative pipelines continuous and nearly instantaneous. In Gentrace, you: - Import and/or construct suites of test data - Use a combination of AI and heuristic evaluators to grade for quality, hallucination, safety, etc - Use our interface to correct automated grades or add your own (yourself or a member of your team) Gentrace integrates at a code level for evaluation, meaning we test your generative AI pipeline the way you would test normal code. This allows you to test more than just prompt changes; for example, you can compare models (eg Claude 2 vs GPT-4 vs GPT 3.5 vs Llama 2) or see the effects of additional chained steps (”Rewrite the previous answer in the following tone:”). Here’s a video overview that goes into a bit more detail: https://youtu.be/XxgDPSrTWIw In production, Gentrace observes for speed, cost, and data flow. It also shows real user feedback as well. We do this by integrating via our SDK at a code level; Gentrace does not proxy requests. Soon, we’ll allow you to convert production data into test cases, allowing customer support to turn bad production generations into “failing tests” for AI teams to make pass. We process interim steps and multiple outputs as well, helping evaluate agent flows / chains where the “last output” isn’t always the only thing that matters. There’s been a lot of observability tools published recently. We differ from those by focusing more strongly on blending observability with strong evaluation and by using an SDK rather than a “man-in-the-middle” approach to capturing data (ie Gentrace can be down and your request to OpenAI will still succeed). Within the evaluation landscape, we differentiate by integrating with code (see above for benefits) for capturing generative outputs and by providing a customizable UI workflow for building evaluators. In Gentrace, you start with off-the-shelf automated evaluators and then customize them to your specific task. You also build and run new evaluators on old generative outputs. Finally, you easily override automated evaluators and/or blend automated evaluation with evaluation by humans on your team. We also focus on being suitable for business use. We are SOC 2 Type 1 compliant (Type 2 coming shortly), have robust legal documentation around data processing, security, and privacy, and have already passed several vendor legal and security reviews at large technology companies. Our standard usage-based pricing is available on the website: https://ift.tt/emtdXBg If you are building features with generative AI, we would love to get your feedback. You can self-serve sign up (without a credit card) for a 14 day trial here: https://gentrace.ai/ We’re available right here for feedback and questions. We’re also available at support@gentrace.ai. Best, Doug, Vivek, and Daniel https://gentrace.ai August 23, 2023 at 11:38PM

Show HN: Cashe - A money library written in Ada https://ift.tt/74zQWRp

Show HN: Cashe - A money library written in Ada Introducing Cashe: a Money library written in Ada 2022! The purpose of Cashe is to give Money its own high-precision datatype taking advantage of Ada's fixed type decimal system[1]. This allows storing money, associated with a currency, at a defined precision with the choice of utilizing fuzzy or exact equality (see readme for more details). It supports ISO Currencies[2] as well as Custom-defined currencies[3], and even a working Currency Exchange[4]. You can install it using Alire, which is Ada's package manager with a simple `alr with cashe` There's quite a bit of examples in the readme if you would like to see what the code looks like, but I also gave full code examples for almost all of the functions in the API Documentation[5]. [1] https://ift.tt/KEFzNrC [2] https://ift.tt/KuVNDR7 [3] https://ift.tt/C4RdPzw... [4] https://ift.tt/OSQTIwX... [5] https://ift.tt/hSLWmx0 https://ift.tt/w3VFie6 August 23, 2023 at 11:21PM

Show HN: To mute words on Twitter in batches, I created a browser extension https://ift.tt/uKhqpMC

Show HN: To mute words on Twitter in batches, I created a browser extension Hello HN community :) For a while now I've been watching my Twitter feed fill up with more and more crap. The fact that it's now possible to monetise your tweets has made things even crappier. At the same time, adding words to mute is a pain. First you have to find the option, buried deep in Twitter's settings, and then you have to add them one by one. So I came up with the idea of writing a little browser extension that lets you add lists of muted words, which can come from more or less anywhere, as long as they're in a certain format (a multi-line text file or a JSON array). The extension doesn't collect any data, you don't need an account to use it, and you can store your lists anywhere (although I'd recommend Github gist or Pastebin). To be honest, I made this mainly as an exercise to learn how a browser extension works and how to make one, but if it's useful to people, that's great! Feel free to let me know what you think and give it a try. If there's ever an audience for it, I'm thinking of taking it further by adding lists of people to mute, extracting your existing list of muted words from Twitter, etc.If you have any other ideas for development, I'd love to hear from you. https://ift.tt/E24uZA5 August 23, 2023 at 06:43PM

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://ift.tt/adVCoQX

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://ift.tt/3MNqkEb August 23, 2023 at 10:56AM

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://ift.tt/oqIVnRs

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://ift.tt/sc38Bqe August 22, 2023 at 11:08PM

Show HN: Scribble with AI – Create social media creatives with AI https://ift.tt/KN81IyA

Show HN: Scribble with AI – Create social media creatives with AI I've been working on a project that will create social media creatives from prompts. This will let users create social media posts quickly. Let me give an example. Suppose I want to make a post on "Give me 8 health benefits of Ginger", it gives me 8 health benefits in the form of images that I can post on my social media. Here's the output -> https://ift.tt/qNVm0LP... If you'd like to try it out with your own prompts you can signup and give it a try. No credit cards is required to get started. I would love to have your feedback about this product. I am also looking for someone who might be interested in this project and is open to mentoring, so that I can learn to market this product and build a business around it. You can reach me out at scribblewithai@gmail.com Thanks! https://ift.tt/4JTrRle August 23, 2023 at 02:36AM

Show HN: A CLI tool and controller to access K8s network through WireGuard https://ift.tt/hBIcNO5

Show HN: A CLI tool and controller to access K8s network through WireGuard Hi everyone! k8s-insider is a CLI tool to manage VPN networks and access Kubernetes workload and service resources directly through a WireGuard tunnel. It started as a simple Helm chart with a linuxserver/wireguard-like container image but, possibly due to my neurodivergence getting the better of me, evolved into a toolbox that, depending on the cluster configuration, can more or less automagically configure multiple networks with dynamic IP assignments and netpol-limited access to the cluster. I’ve found it to be a perfect middle ground between juggling multiple port-forwards and deploying something like Tailscale to the cluster. And it’s written in Rust, which made it oh-so-lovely to work on. :> https://ift.tt/BIjSv1Y August 22, 2023 at 10:30PM

Show HN: creativechronicles.org – A video archive from notable startups/founders https://ift.tt/OtbnAVi

Show HN: creativechronicles.org – A video archive from notable startups/founders https://ift.tt/SmNIiyA August 23, 2023 at 12:25AM

Show HN: Convert Research Papers into Dynamic Mind Maps with Claude https://ift.tt/G5D3J8w

Show HN: Convert Research Papers into Dynamic Mind Maps with Claude https://ift.tt/ZCd8QSA August 22, 2023 at 03:35PM

Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania https://ift.tt/mtLN30D

Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania This was my entry for a Metroidvania Month game jam last year. I like how Metroidvanias make you rethink movement as the game goes on, and since I didn't want to design combat I focused on that. But I didn't want the different mechanics to be objects you pick up. The theme for the jam was "shapeshifting", which suggested the unusual mechanic seen here. Fortunately I'd forgotten about Snakebird or I might not have been bold enough to make the gravity+snake parts so prominent. And in the year since this came out, there have been at least three cool puzzle games nearby in design space: - Tetronimeow https://ift.tt/RErYMuw has a heavy focus on rotation (which I skipped to avoid confusion), it gets much more Metroidvania mileage out of the central idea - Growmi https://ift.tt/jmLP63u does a great job building mechanics out of the snake+gravity idea - The Plumber Thing https://ift.tt/iJVAp3m If this looks familiar, I did post a Show HN last year, but dang invited me to re-submit it. I kept putting it off in hopes I could make a big splash when launching a new version: I have some ideas for touchscreens (currently keyboard only) and for an earlier game with more restricted abilities (no free transformation, then swapping with just one previous shape). But it's looking unlikely that I'll revisit it. https://ift.tt/pcWQyP3 August 22, 2023 at 10:11AM

Show HN: SQL Formatter https://ift.tt/gLuF7Nh

Show HN: SQL Formatter https://ift.tt/o9cFIej August 22, 2023 at 03:01AM

Show HN: VisionScript, abstract programming language for computer vision https://ift.tt/wZQPz4k

Show HN: VisionScript, abstract programming language for computer vision Hello! I'm James and I am working on VisionScript. With VisionScript, I want to empower people -- including everyone without any prior programming experience -- to build cool apps with vision. This weekend, I recorded a demo for VisionScript, in which I made apps that count how many cats are in an image and hides people in a video. Each app was < 10 lines of code. https://vimeo.com/856043804 VisionScript is built for the 10 year old inside of me who would have loved more visual programming languages with which to play. I want to show people the potential of programming and how you can make what you want with computers, whether it be a game that counts cats or an app that monitors how many birds flew past a tree. Those "wow" moments should come as soon as possible in one's learning experience. VisionScript is in active development. I started work on this project in July. There will likely be bugs; this is a passion project. Inspiration comes from Wolfram and Python. Behind the scenes, I am adopting what I am calling "lexical inference", which is to say there is a last state value on which functions infer; the language manages types and state. https://github.com/capjamesg/visionscript August 22, 2023 at 01:48AM

Show HN: Blast, A Load generator for TCP servers https://ift.tt/TjbsczQ

Show HN: Blast, A Load generator for TCP servers https://ift.tt/XOyzVSQ August 21, 2023 at 09:16PM

Show HN: My husband quit his job to build a new social audio app with Flutter https://ift.tt/HzQhFEC

Show HN: My husband quit his job to build a new social audio app with Flutter Wife of an app-builder here. My husband quit his full time job at Apple to work full-time last year on a new social audio app where you are anonymous and there are no videos or images - people can only connect with their voice. The app has been up for just less than 2 months, and it was incredible to see 300 users from all around the world leave voice messages of support for each other. It definitely restored my faith in humanity, so much so that I decided to jump on board as a co-founder :) We are on a mission to end loneliness that is gripping our world today, and we hope you also come onboard to get or offer support, or even just to make authentic connections with people around the world. https://ift.tt/iwSbk7B August 22, 2023 at 12:09AM

Show HN: superwhisper – AI powered offline voice to text for macOS https://ift.tt/mvRHX0G

Show HN: superwhisper – AI powered offline voice to text for macOS Hey HN, I built superwhisper out of frustration with the native dictation capabilities of macOS. Inaccurate, required manual punctuation, didnt activate in some contexts or would have audio capture issues. I wanted a replacement that worked offline, had cross language support, was configurable and worked in any application. Under the hood the app is using whisper.cpp, which runs really well on the Apple Silicon chips. You can use the base and standard size models for free, larger models sizes and languages other than english are paid. Let me know what you think! For context, I launched this just one month ago and have been rapidly adding features and making fixes. If you want to follow along with development, I post release info on twitter ( https://ift.tt/FS9Upyv ) or you can subscribe to emails via the form on the website (very bottom). https://ift.tt/Ba1Igns August 21, 2023 at 09:03AM

Show HN: Efficiently Query BigQuery and Snowflake from Postgres https://ift.tt/MSn7Dbt

Show HN: Efficiently Query BigQuery and Snowflake from Postgres https://ift.tt/FfG1gXe August 21, 2023 at 09:01AM

Show HN: Simple open-source tool for mocking using TS interfaces https://ift.tt/PCmGFqr

Show HN: Simple open-source tool for mocking using TS interfaces https://ift.tt/lE9rPmg August 21, 2023 at 03:53AM

Show HN: HTBL – A stupid way to write back ends in HTML https://ift.tt/XBn8AaP

Show HN: HTBL – A stupid way to write back ends in HTML https://ift.tt/GITsZUo August 21, 2023 at 02:05AM

Show HN: Cubisum – A number puzzle game inspired by Sudoku and Minesweeper https://ift.tt/F0XAKHu

Show HN: Cubisum – A number puzzle game inspired by Sudoku and Minesweeper Hi HN, I'd like to share a logic number puzzle game I created! It is somewhat reminiscent of Sudoku and Minesweeper, but with its own twist. The rules are simple but it can be quite challenging! Please enjoy :) The feedback on the game prototype was invaluable and I incorporated a lot into what I hope is a more polished version of the game. What's new: Introduced a daily puzzle challenge. Dark mode. Enhanced user experience with improved UI. I'd love to hear your thoughts on these updates. Feedback is always appreciated! https://cubisum.com/ August 21, 2023 at 01:14AM

Show HN: Easy Sell AI – AI that sells for you on marketplace apps https://ift.tt/YC4uskp

Show HN: Easy Sell AI – AI that sells for you on marketplace apps Hey Hacker News! I've developed Easy Sell AI to address the challenges I faced when I had to quickly sell items on platforms like Facebook Marketplace and OfferUp. Problem: 1. Constantly getting lowballed by potential buyers, and I just didn't know what I needed to say to get the price I wanted. 2. Spending hours negotiating with potential buyers, only to often get ghosted. 3. Encountering fake accounts and scammers, making the process even more tedious. Solution: Enter Easy Sell AI, an AI-powered tool that does all the selling for you on Marketplace Apps. With it: 1. The AI takes over negotiations, giving the perfect line to get you the price you deserve. 2. You're only notified when a genuine deal is on the table. 3. Set your preferences, like your minimum acceptable price and availability, and let Easy Sell AI manage the rest. Check it out and let me know your thoughts! https://easysell.ai August 20, 2023 at 09:24PM

Show HN: Just intonation keyboard – play music without knowing music https://ift.tt/vHQAxiu

Show HN: Just intonation keyboard – play music without knowing music This is a keyboard in just intonation. It can play the notes a piano can. The big difference from a piano is that all the notes become consonant. You can play without knowing any music theory. Hit arbitrary notes with the rhythm you want, and the pitches will work. Not understanding the buttons is fine. Even rolling your elbow around your keyboard is fine. If you are a musician and press the wrong key while playing a song, it will still fit. It will sound like you made an intelligent, conscious choice to play another note, even though you know in your heart it was an accident. Beginner jazz musicians rejoice. It's not an AI making choices for you; it's just a very elegant interface. What makes this possible is several new discoveries in psychoacoustics about how harmony works. While a piano lays out notes in pitch space, this keyboard is able to lay out notes in consonance space. When you play random notes, they tend to be "close together" on the physical keyboard. Distance on the keyboard maps well to distance in consonance space, so those random notes are close together in consonance space and sound good together. According to Miles Davis, a "wrong" note becomes correct in the right context. If you try to play a wrong note, the purple buttons you press will automatically land you in the right context, even if you don't know what that context is yourself. So you can stumble your way through an improv and the keyboard will offer the right notes without needing you to think about it. Harmonic consonance of chords can be read directly off the numbers in the keyboard, which implies that these numbers are a good language to think about music with. It doesn't take years of training, just reading the rules. The subset of playable songs is different from a piano, which means that songs in your existing piano repertoire will snip off some notes. Hardware for thumb keys would fix this, so you could play your existing piano songs in full, plus other songs a piano can't play. I don't have such hardware so I haven't implemented this. The other way is to have two keyboards and a partner. The remaining issue is that there is no sheet music in just intonation. Unfortunately, I have had no success in finding piano sheet music in a common, interpretable format. So while I do have a converter from 12 equal temperament to just intonation, there are no input files to use it with... https://ift.tt/wbV01Lx August 20, 2023 at 05:49AM

Show HN: NES emulator with network multiplayer written in Go https://ift.tt/hHLRlN5

Show HN: NES emulator with network multiplayer written in Go https://ift.tt/gBm0tXs August 19, 2023 at 11:05PM

Show HN: CatGPT - Expert answers to any cat-related questions https://ift.tt/y26WK5D

Show HN: CatGPT - Expert answers to any cat-related questions https://ift.tt/7l5xKLh August 19, 2023 at 09:44PM

Show HN: Semi-Autonomous LLM with a dev workstation https://ift.tt/jMV0NOz

Show HN: Semi-Autonomous LLM with a dev workstation https://devassistant.ai August 19, 2023 at 10:33PM

Show HN: Aviation navigation log on $20 receipt printer https://ift.tt/KwWZBN5

Show HN: Aviation navigation log on $20 receipt printer https://ift.tt/kPSCHVM August 19, 2023 at 11:57PM

Show HN: Linguist, a translation browser extension https://ift.tt/kvm2pBI

Show HN: Linguist, a translation browser extension Hey everyone, check the Linguist - you can translate texts offline - dictionary + history for learn languages - it is are hackable - you can enter code to use your own translation service https://ift.tt/P2dAeyx August 19, 2023 at 09:28PM

Show HN: A simple, open-source Notion-like avatar generator https://ift.tt/UutFlzr

Show HN: A simple, open-source Notion-like avatar generator https://ift.tt/S1Az4v6 August 19, 2023 at 07:32PM

Show HN: AI that summarize news and analyze potential stock impact https://ift.tt/FGjBv0c

Show HN: AI that summarize news and analyze potential stock impact Hi Everyone, I was frustrated with the terrible news reading experience (Paywall, advertisements) so I created a free tool that summarizes the latest news articles and analyzes the potential stock impacts. This experiment has saved me so much time to help me understand what might be more important than others. It's completely free, no ad whatsoever. However, AI is a blackbox so take the rating (positive, negative, long-term, and short-term impact) with a grain of salt. It may have picked up some nuances within the article to give a rating and you might not agree with it. Please let me know if you have any feedback! https://ift.tt/v1JzHRI August 19, 2023 at 04:45AM

Show HN: Saf – simple, reliable, rsync-based, battle tested, rounded backup https://ift.tt/qF2Pcug

Show HN: Saf – simple, reliable, rsync-based, battle tested, rounded backup I had this backup code working reliably for years, using local file system, vps/dedicated server, or remote storage for backup, then I finally get time to wrap README, iron few missing switches and publish. Should be production ready and reliable, so it could be useful to others. Contributors are welcome. < https://github.com/dusanx/saf > https://ift.tt/r7HNOsk August 19, 2023 at 04:19AM

Show HN: This project allows you to easily implement parallel training https://ift.tt/cXwflUh

Show HN: This project allows you to easily implement parallel training https://ift.tt/Xf4eKMm August 18, 2023 at 07:01PM

Show HN: Superlines.io – The all-in-one AI marketing solution https://ift.tt/IXD0OxQ

Show HN: Superlines.io – The all-in-one AI marketing solution Superlines is an all-in-one marketing solution that automates content creation, analysis, optimization, and testing - basically, it takes care of the daily grind for marketing teams. Core target group are marketers such as social media managers, copywriters, content marketers, or marketing directors looking to scale their marketing team's impact without increasing resources. Many AI tools are popping up all the time but Superlines is different as it covers all major marketing use cases in one platform rather than being only focused, eg. on text generation. Our most popular feature is our landing page optimizer, which analyzes landing page content and instantly creates improvements. Just provide a URL and rock on. Superlines lets marketers input their brand and business details to their Brand settings and Superlines uses this knowledge to customize it's output. We've just launched in AppSumo and gotten a ton of feedback. https://ift.tt/StTonrQ Check it out and just tell me what you think. https://ift.tt/E8dKJsZ August 18, 2023 at 06:44PM

Show HN: Run globally distributed full-stack apps on high-performance MicroVMs https://ift.tt/Dyjmnsw

Show HN: Run globally distributed full-stack apps on high-performance MicroVMs Hi HN! We’re Yann, Edouard, and Bastien from Koyeb ( https://www.koyeb.com/ ). We’re building a platform to let you deploy full-stack apps on high-performance hardware around the world, with zero configuration. We provide a “global serverless feeling”, without the hassle of re-writing all your apps or managing k8s complexity [1]. We built Scaleway, a cloud service provider where we designed ARM servers and provided them as cloud servers. During our time there, we saw customers struggle with the same issues while trying to deploy full-stack applications and APIs resiliently. As it turns out, deploying applications and managing networking across a multi-data center fleet of machines (virtual or physical) requires an overwhelming amount of orchestration and configuration. At the time, that complexity meant that multi-region deployments were simply out-of-reach for most businesses. When thinking about how we wanted to solve those problems, we tried several solutions. We briefly explored offering a FaaS experience [2], but from our first steps, user feedback made us reconsider whether it was the correct abstraction. In most cases, it seemed that functions simply added complexity and required learning how to engineer using provider-specific primitives. In many ways, developing with functions felt like abandoning all of the benefits of frameworks. Another popular option these days is to go with Kubernetes. From an engineering perspective, Kubernetes is extremely powerful, but it also involves massive amounts of overhead. Building software, managing networking, and deploying across regions involves integrating many different components and maintaining them over time. It can be tough to justify the level of effort and investment it takes to keep it all running rather than work on building out your product. We believe you should be able to write your apps and run them without modification with simple scaling, global distribution transparently managed by the provider, and no infrastructure or orchestration management. Koyeb is a cloud platform where you come with a git repository or a Docker image, we build the code into a container (when needed), run the container inside of Firecracker microVMs, and deploy it to multiple regions on top of bare metal servers. There is an edge network in front to accelerate delivery and a global networking layer for inter-service communication (service mesh/discovery) [3]. We took a few steps to get the Koyeb platform to where it is today: we built our own serverless engine [4]. We use Nomad and Firecracker for orchestration, and Kuma for the networking layer. In the last year, we spawned six regions in Washington, DC, San Francisco, Singapore, Paris, Frankfurt and Tokyo, added support for native workers, gRPC, HTTP/2 [5], WebSockets, and custom health checks. We are working next on autoscaling, databases, and preview environments. We’re super excited to show you Koyeb today and we’d love to hear your thoughts on the platform and what we are building in the comments. To make getting started easy, we provide $5.50 in free credits every month so you can run up to two services for free. P.S. A payment method is required to access the platform to prevent abuse (we had hard months last year dealing with that). If you’d like to try the platform without adding a card, reach out at support@koyeb.com or @gokoyeb on Twitter. [1] https://ift.tt/o0liYpF... [2] https://ift.tt/OizghT7... [3] https://ift.tt/5RO4pFN... [4] https://ift.tt/ay5ebA6... [5] https://ift.tt/KQw6J1d... https://www.koyeb.com/ August 17, 2023 at 05:45PM

Show HN: Create your own Discover Weekly https://ift.tt/GNwLhpR

Show HN: Create your own Discover Weekly Choose a few playlists to get new tracks from, and they'll be filtered out every Monday to a new playlist. Kind of like Discover Weekly, but you get to choose the music sources. Hope you enjoy, and I would love feedback! https://ift.tt/3lfhAt6 August 17, 2023 at 09:47PM

Show HN: Interactive exercises for GNU grep, sed and awk https://ift.tt/Zuq7h8G

Show HN: Interactive exercises for GNU grep, sed and awk Hello! For the past few months, I've been using a Python framework called Textual to create TUI apps for interactive exercises. Released the app for GNU awk earlier today, so thought I'd create a post here. If you already know how to manage Python packages, you can use the following command to get all the three apps: pip install grepexercises sedexercises awkexercises `pipx` should also work, but I haven't tested it. The GitHub repo has the source code as well as more detailed installation instructions. You can use alternative CLI tools to solve these exercises as well. For example, Perl instead of GNU awk or ripgrep instead of GNU grep and so on. Hope you find these TUI apps useful. I'd highly appreciate your feedback. Happy learning :) https://ift.tt/CpmL6UG August 17, 2023 at 05:13PM

Show HN: I resurrected one of the top dead Show HNs https://ift.tt/H1m5j0z

Show HN: I resurrected one of the top dead Show HNs OneView was first posted to HN in 2017, but died sometime around late 2019. Using the web archive I cobbled together something that works. According to this[0], oneview is the #5 top dead show hn. [0] https://ift.tt/xlOeXq1... https://ift.tt/uxloyVX August 17, 2023 at 09:56PM

Show HN: Strich – Barcode scanning for web apps https://ift.tt/5XQKP8J

Show HN: Strich – Barcode scanning for web apps Hi, I'm Alex - the creator of STRICH ( https://strich.io ), a barcode scanning library for web apps. Barcode scanning in web apps is nothing new. In my previous work experience, I've had the opportunity to use both high-end commercial offerings (e.g. Scandit) and OSS libraries like QuaggaJS or ZXing-JS in a wide range of customer projects, mainly in logistics. I became dissatisfied with both. The established commercial offerings had five- to six-figure license fees and the developer experience was not always optimal. The web browser as a platform also seemed not to be the main priority for these players. The open source libraries are essentially unmaintained and not suitable for commercial use due to the lack of support. Also the recognition performance is not enough for some cases - for a detailed comparison see https://ift.tt/UV937uf Having dabbled a bit in Computer Vision topics before, and armed with an understanding of the market situation, I set out to build an alternative to fill the gap between the two worlds. After almost two years of on-and-off development and 6 months of piloting with a key customer, STRICH launched at beginning of this year. STRICH is built exclusively for web browsers running on smartphones. I believe the vast majority of barcode scanning apps are in-house line of business apps that benefit from distribution outside of app stores and a single codebase with abundant developer resources. Barcode scanning in web apps is efficient and avoids platform risk and unnecessary costs associated with developing and publishing native apps. https://strich.io August 17, 2023 at 08:24PM

Show HN: How to use LLMs to generate accurate SQL for real-world data https://ift.tt/gkju8w9

Show HN: How to use LLMs to generate accurate SQL for real-world data Hey HN, We are Zain and Ashish, founders of Vanna AI. We recently embarked on an experiment to see if large language models (specifically LLMs) could help in generating SQL queries for real-world datasets. We initially started this project as a web app but realized that it was most useful and had broadest applicability as a Python package since you can then incorporate it into an existing workflow (Jupyter notebook, Slackbot, etc). We've had some good success with customer datasets but we've generally heard a lot of skepticism so we decided to write a paper about the methodology we're using and how various LLMs compare. Let us know if you have any questions or requests. The underlying Python package is open source. There is a server component to store and retrieve metadata but by next week there will be a fully open-source and locally runnable version. Cheers! https://ift.tt/MjwSq8o August 17, 2023 at 07:17PM

Show HN: Rules – Shortcuts Automation Based on Calendar Events https://ift.tt/tSeXToL

Show HN: Rules – Shortcuts Automation Based on Calendar Events Read and thought once too often that "This would be trivial if Calendar Events were triggers for Personal Shortcuts Automations". So decided to create a Mac app for it. The app works similar to Rules in Mail: - Specify some conditions (e.g. Calendar is "Work", Location contains "zoom") - Choose shortcuts to run on events that meet the conditions - you can have multiple actions, each with a different offset and custom input Good to know: - The app can only trigger automations while your Mac is awake (missed actions can be triggered on wake up) - The free version offers full functionality, but is limited to a max of 2 rules. Pro is a one-time purchase - All your data stays on device + no ads or data collection I would appreciate any feedback, especially what automations you might use the app for https://ift.tt/TESpsD1 August 17, 2023 at 03:53PM

Show HN: Marqo – Vectorless Vector Search https://ift.tt/garsC60

Show HN: Marqo – Vectorless Vector Search Marqo is an end-to-end vector search engine. It contains everything required to integrate vector search into an application in a single API. Here is a code snippet for a minimal example of vector search with Marqo: mq = marqo.Client() mq.create_index("my-first-index") mq.index("my-first-index").add_documents([{"title": "The Travels of Marco Polo"}]) results = mq.index("my-first-index").search(q="Marqo Polo") Why Marqo? Vector similarity alone is not enough for vector search. Vector search requires more than a vector database - it also requires machine learning (ML) deployment and management, preprocessing and transformations of inputs as well as the ability to modify search behavior without retraining a model. Marqo contains all these pieces, enabling developers to build vector search into their application with minimal effort. Why not X, Y, Z vector database? Vector databases are specialized components for vector similarity. They are “vectors in - vectors out”. They still require the production of vectors, management of the ML models, associated orchestration and processing of the inputs. Marqo makes this easy by being “documents in, documents out”. Preprocessing of text and images, embedding the content, storing meta-data and deployment of inference and storage is all taken care of by Marqo. We have been running Marqo for production workloads with both low-latency and large index requirements. Marqo features: - Low-latency (10’s ms - configuration dependent), large scale (10’s - 100’s M vectors). - Easily integrates with LLM’s and other generative AI - augmented generation using a knowledge base. - Pre-configured open source embedding models - SBERT, Huggingface, CLIP/OpenCLIP. - Pre-filtering and lexical search. - Multimodal model support - search text and/or images. - Custom models - load models fine tuned from your own data. - Ranking with document meta data - bias the similarity with properties like popularity. - Multi-term multi-modal queries - allows per query personalization and topic avoidance. - Multi-modal representations - search over documents that have both text and images. - GPU/CPU/ONNX/PyTorch inference support. See some examples here: Multimodal search: [1] https://ift.tt/KwLmnFu... Refining image quality and identifying unwanted content: [2] https://ift.tt/shuoMTQ... Question answering over transcripts of speech: [3] https://ift.tt/Z1lM2Oz Question and answering over technical documents and augmenting NPC's with a backstory: [4] https://ift.tt/74S8rIL... https://ift.tt/Q3RmqfI August 16, 2023 at 09:01PM

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts https://ift.tt/r92Spwn

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts This JS library provides basic axioms for building and managing GPT prompts. It helps you build small and reusable prompt components and then let you compose them together to build larger ones. https://ift.tt/Gbhlj8Q August 16, 2023 at 07:19PM

Show HN: Watermelon – Source-available passive documentation search engine https://ift.tt/MHPbGwA

Show HN: Watermelon – Source-available passive documentation search engine Hey there HN! We're a pair of devs and we are looking to get feedback for our source-available passive documentation search engine. Passive documentation is the code context devs are generating as they talk about code in systems such as GitHub, Slack, Notion and Jira. Our search engine serves both our IDE extension (for individuals) and GitHub app (for teams). As devs we know that there are certain PRs that stay unmerged for weeks or even months, not because of the technical complexity, but because of the debate that they produce around changes in the business logic: "Will this change really improve our metrics?" We know that non-technical stakeholders (managers and designers) can bring a more holistic view to these debates but code review is too technical for them. So we decided to build this with the premise of "let's contextualize devs with business logic". We’re starting with a GitHub app that contextualizes Pull Requests with pieces of related passive documentation. Our big vision is to build a copilot for engineering leaders, starting by automating code review. If we're already indexing passive documentation tied to a new PR, we suspect that we can provide a "first health check" to a PR and say whether or not it's meeting the business requirements. Here's the repo if you want to check it out: https://ift.tt/rvwZky0 And here's a blog post explaining why we made our search engine source-available: https://ift.tt/HYhAiMr... Please give us your feedback! Thanks. https://ift.tt/rvwZky0 August 14, 2023 at 09:47PM

Show HN: Lottielab – Create product animations in the browser easily https://ift.tt/qUYPBR5

Show HN: Lottielab – Create product animations in the browser easily Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating! https://ift.tt/wL5nhtQ August 15, 2023 at 07:28PM

Show HN: Free, Offline, Article Reader for iOS https://ift.tt/Hif0Nwe

Show HN: Free, Offline, Article Reader for iOS https://ift.tt/Jlgb8L4 August 16, 2023 at 02:24AM

Show HN: Exploring the design space of binary search trees https://ift.tt/F6uAGCl

Show HN: Exploring the design space of binary search trees https://ift.tt/G1AWMoI August 15, 2023 at 09:34PM

Show HN: I wrote 100 book summaries https://ift.tt/Uw8ocKd

Show HN: I wrote 100 book summaries https://ift.tt/i9Ca8rg August 16, 2023 at 12:28AM

Show HN: Layerform (YC S23) – Open-source dev environments using Terraform files https://ift.tt/85hV0et

Show HN: Layerform (YC S23) – Open-source dev environments using Terraform files Hi HN, we're Lucas and Lucas, the authors of Layerform (https://ift.tt/ZwPNaeo). Layerform is an open-source tool for setting up development environments using plain .tf files. We allow each engineer to create their own "staging" environment and reuse infrastructure. Whenever engineers run layerform spawn, we use plain .tf files to give them their own "staging" environment that looks just like production. Many teams have a single (or too few) staging environments, which developers have to queue to use. This is particularly a problem when a system is large, because then engineers can't run it on their machines and cannot easily test their changes in a production-like environment. Often they end up with a cluttered Slack channel in which engineers wait for their turn to use staging. Sometimes, they don't even have that clunky channel and end up merging broken code or shipping bugs to production. Lucas and I decided to solve this because we previously suffered with shared staging environments. Layerform gives each developer their own production-like environment.This eliminates the bottleneck, increasing the number of deploys engineers make. Additionally, it reduces the amount of bugs and rework because developers have a production-like environment to develop and test against. They can just run "layerform spawn" and get their own staging. We wrap the MPL-licensed Terraform and allow engineers to encapsulate each part of their infrastructure into layers. They can then create multiple instances of a particular layer to create a development environment.The benefit of using layers instead of raw Terraform modules is that they're much easier to write and reuse, meaning multiple development environments can run on top of the same infrastructure. Layerform's environments are quick and cheap to spin up because they share core pieces of infrastructure. Additionally, Layerform can automatically tag components in each layer, making it easier for FinOps teams to manage costs and do chargebacks. For example: with Layerform, a product developer can spin up their own lambdas and pods for staging while still using a shared Kubernetes cluster and Kafka instance. That way, development environments are quicker to spin up and cheaper to maintain. Each developer's layer also gets a tag, meaning FinOps teams know how much each team's environments cost. For the sake of transparency, the way we intend to make money is by providing a managed service with governance, management, and cost-control features, including turning off environments automatically on inactivity or after business hours. The Layerform CLI itself will remain free and open. You can download the Layerform CLI right now and use it for free. Currently, all the state, permissions, and layer definitions stay in your cloud, under your control. After the whole license change thing, I think it's also worth mentioning we'll be building on top of the community's fork and will consider adding support for Pulumi too. We'd love your feedback on our solution to eliminate “the staging bottleneck". What do you think? August 15, 2023 at 09:15PM

Show HN: Anonymize HN – a Chrome extension to anonymize Hacker News users https://ift.tt/An0bBQS

Show HN: Anonymize HN – a Chrome extension to anonymize Hacker News users I wrote a small Chrome extension that allows the user to replace all usernames on Hacker News with either the string `anonymous` or a deterministic hashed value. https://ift.tt/bCNL2jc August 15, 2023 at 12:36AM

Show HN: Detect whether an image was made by AI or Not https://ift.tt/FEDLbSg

Show HN: Detect whether an image was made by AI or Not https://ift.tt/aAJjBQ4 August 15, 2023 at 12:29AM

Show HN: CoolReadME, a way to display GitHub profile readmes with custom CSS https://ift.tt/PrAw2f8

Show HN: CoolReadME, a way to display GitHub profile readmes with custom CSS https://ift.tt/46ewpPX August 15, 2023 at 12:12AM

Show HN: Epsilla – Open-source vector database with low query latency https://ift.tt/GJnsKV2

Show HN: Epsilla – Open-source vector database with low query latency Hey HN! We are building Epsilla ( https://ift.tt/BcriPlj ), an open-source, self-hostable vector database for semantic similarity search that specializes in low query latency. When do we need a vector database? For example, GPT-3.5 has a 16k context window limit. If we want to let it answer a question about a 300 page book, we cannot put the whole book content into the context. We have to choose the sections of the book that are most relevant to the question. Vector database is specialized at ranking and picking the most relevant content from a large pool of documents based on their semantic similarity. Most vector databases utilize hierarchical navigational small world (HNSW) for indexing the vectors for high precision vector search, and its latency significantly degrades when the precision target is higher than 95%. At a previous company, we worked on building the parallel graph traversal engine. We realized that the bottleneck of HNSW performance is because there are too many sequential traversal steps that don't fully leverage multi-core CPU computation resources. After some research, we found that there are algorithms such as SpeedANN that are targeting this problem, which is not leveraged by industry yet. So we built the Epsilla vector database to turn the research into a production system. With Epsilla, we shoot for 10x lower vector search latency compared to HNSW based vector databases. We did an initial benchmark against the top open source vector databases: https://ift.tt/d0sOaiC... We provide a Docker image for you to install Epsilla backend locally, and provide a Python client and a JavaScript client to connect and interact with it. Quickstart: docker pull epsilla/vectordb docker run --pull=always -d -p 8888:8888 epsilla/vectordb pip install pyepsilla git clone https://ift.tt/Sb2OFlk cd examples python hello_epsilla.py We just started a month ago. We'd love to hear what you think, and more importantly, what you wish to see in the future. We are thinking about a serverless vector database on cloud with a consumption based pricing model, and we are eager to get your feedback. https://ift.tt/BcriPlj August 14, 2023 at 10:21PM

Show HN: A website chatbot that also uses APIs https://ift.tt/OrIBdjt

Show HN: A website chatbot that also uses APIs Hi! "Another chatbot for your content" you may ask? Not really! Let me explain. I have realized that there's an untapped potential for ChatGPT plugins: why leave them locked up in the OpenAI store? Let's embed them on websites or share using links! Let's make chatbots ~ do stuff ~, not just talk about what they know. That's how Chatwith was born. It is a chat widget, it scrapes your website, knowledge page, notion etc - but more importantly, it also understands your API. It can interact with that API on your or your visitors' behalf. Some use cases & ideas: - Shopify bot - ask it for order status and invoice - Realtor - ask for budget, provide listings - Survey - ask questions, collect answers, submit to Typeform - Airline service - get your boarding pass - Mixpanel - talk to your analytics In other words: - Talk to APIs & hot data - ChatGPT plugin on every website - Your SaaS can be a chatbot - APIs made accessible (they were reserved for devs until now) - Create an API, use chat as the interface - skip the frontend I am trying to envision a future where website visitors are empowered to just say what they want from the business - instead of navigating endless dashboards and documentation. I'm looking for some feedback about my product! lmk Rafal https://chatwith.tools August 14, 2023 at 07:08PM

Show HN: Generate a free User Persona in 10 seconds https://ift.tt/HqB4Qw6

Show HN: Generate a free User Persona in 10 seconds I hate talking to people. So I made ChatGPT do it for me. https://ift.tt/jRuin0V August 14, 2023 at 06:29PM

Show HN: I made a tool that turns images into videos to boost our Twitter reach https://ift.tt/LpRFTkK

Show HN: I made a tool that turns images into videos to boost our Twitter reach Recently there were some changes to the Twitter algorithm and one of the most important ones was boosting video content even more in the feed, which got me thinking: "Why shouldn't we benefit from the algo changes and get a boost every time we are sharing some visuals?" So I spent the weekend building a tool that: - Turns your images into videos - Has 30 beautiful animated gradients that we can pick from - Is completely FREE I'd love to know your thoughts about it! https://ift.tt/6CVmDAF August 14, 2023 at 06:19PM

Show HN: A free course on how to write a good Midjourney/ChatGPT prompt https://ift.tt/q3rTw9F

Show HN: A free course on how to write a good Midjourney/ChatGPT prompt https://ift.tt/0ubLcdU August 14, 2023 at 04:37PM

Show HN: Zero-dependency minimal Java web framework https://ift.tt/5eGDxRk

Show HN: Zero-dependency minimal Java web framework I have written a from-scratch minimalist Java web framework, called Minum. I'd like to get your thoughts. The driving goal has been achieving characterics of plainness, frugality, performance, maintainability, testability, and ease of use. It has zero dependencies other than Java's SDK, yet provides a web server, routing, authentication, testing, logging, templating, HTML parsing, and a database, in 3800 lines of code, compiling to a 150k binary. It currently supports a web application in production. There are also example projects demonstrating its use, linked in the documentation. As the framework itself has no dependencies, it is built using GNU Make. The example applications that depend on it, however, use Maven as their build tool. Because Minum is still in beta, it is not yet published to Maven - but there are instructions for a workaround. The framework and example apps require Java 20. https://ift.tt/cATrgiK August 14, 2023 at 04:15AM

Show HN: PitchPower – AI powered proposal generation for consultants https://ift.tt/EBrPkAe

Show HN: PitchPower – AI powered proposal generation for consultants Hey HN! I'm an indie hacker who builds SAAS products in my free time. I've got a friend who runs a small consulting firm and said this would be a useful tool for them so i thought why not release it as a standalone online tool for everyone. Basically the premise is, you enter some information about your services (or we just scrape your website and figure it out). Then you enter a description of the client brief, tweak the outline, and out comes a unique tailored proposal that you can tweak with AI. That's pretty much it! Would love to hear your thoughts. Thank you. https://ift.tt/8F9xrn5 August 14, 2023 at 02:32AM

Show HN: PokerWave – Retro PvP Card Games in Rust and Redis and VanillaJS https://ift.tt/LK4Sx6l

Show HN: PokerWave – Retro PvP Card Games in Rust and Redis and VanillaJS Source code: https://ift.tt/PRJB1s4 https://pokerwave.io August 14, 2023 at 12:05AM

Show HN: Broken Bear, the AI teddy bear that loves your broken self https://ift.tt/oBO3IxF

Show HN: Broken Bear, the AI teddy bear that loves your broken self I made a GPT-based AI Chatbot based on Carl Roger's philosophy of radical self-acceptance. Broken Bear is designed to be a kind, comforting, and quietly encouraging friend. https://brokenbear.com/ August 13, 2023 at 04:47PM

Show HN: Mixtape of 200 “futuristic” songs circa 1980 https://ift.tt/7ToQfKN

Show HN: Mixtape of 200 “futuristic” songs circa 1980 I'm posting this long mix of 200 "futuristic" music recordings, in chronological order (from the mid 1970's to the mid 1980's). Some are obvious (eg: "She Blinded Me With Science") while others are long forgotten (eg: G.G. Tonet's "Dedicated To Norbert Wiener" or Jyl's "Silicon Valley") --- Circa 1980 Mixtape https://ift.tt/XfYVvhq --- While the theme of the linked mix (ie: tech) probably interests some here, it is likely too fluffy for many others so apologies for that. This thing took me almost two years to finish, so in a moment of weakness I am going ahead and posting it here. There actually is a tech angle to why it took so long. After I gathered the 200 audio tracks I wanted, I wound up stymied for several months because trying to match the timbre and loudness of 200 songs overwhelmed me. During that time I began writing a program in my spare time to band-split all the files and match their perceived loudness. I got around half-way through that when OpenAI released GPT4. On a whim, I asked it to write a BASH script to perform the auto-EQ: a couple evenings of minor tweaks and it was done https://ift.tt/glfNBZM so I went ahead and completed the mix. The final mixing together of songs - I am not a DJ and have no experience beat-matching - was also done programmatically (wrote a program that takes start- and end- times of the regions to crossfade, and then ramps samplerate up or down for the two tracks. August 13, 2023 at 03:02PM

Show HN: I used AI to turn people into GigaChads https://ift.tt/QsEcARD

Show HN: I used AI to turn people into GigaChads Hey folks! I want to share a project I've been working on during my free time over the past few months. It's a mobile app that uses AI to turn people into over 30 famous meme images: from GigaChad to DiCaprio. You can check out some of the results here: https://mememes.app/ I was inspired by the Remix option in Midjourney. At the end of 2022 I saw an article how people using this feature combine two pictures and get some crazy results mixing people with animals and generating new memes. Later, to have a little fun, I decided to prank my friend using the Midjourney Remix with his photos. However, I wasn't satisfied with the results. So I built my own pipeline using Stable Diffusion + DreamBooth + some other components, and created a few images by mixing his face with memes. My friend had a good laugh when he saw them. I thought it would be a good idea to make the process easier to repeat so I built MeMemes app. I hope you all enjoy it and have some fun, and would love to hear your feedback! P.S: Due to high server cost I take small fee for generation. But today I will make it just 1$. https://mememes.app August 13, 2023 at 11:12AM

Show HN: FalkorDB fork from RedisGraph bringing it back to life https://ift.tt/QODVbHZ

Show HN: FalkorDB fork from RedisGraph bringing it back to life The team behind RedisGraph decided to take a stab at bringing this disruptive technology back to market. We plan to rebrand it and release it as a stand alone product, following the same guidelines we have followed for the last 6 years: * Working in the open with the community * Always provide superior performance. * Easy to adapt https://ift.tt/T2O5D1F August 13, 2023 at 04:02AM

Show HN: Run LLaMa2 on the Browser with Ggml.js https://ift.tt/EMYr6kg

Show HN: Run LLaMa2 on the Browser with Ggml.js You can now build serverless AI inference web application with ggml.js's LM backends. https://ift.tt/HadK39o August 13, 2023 at 02:52AM

Show HN: React Hooks in Python https://ift.tt/uYiNtm6

Show HN: React Hooks in Python A React inspired way to code in Python. Python Hooks is a very opinionated project and it's not meant to be a replacement for any of the existing state management libraries. It was created as a coding exercise gone sideways. https://ift.tt/oNODRcT August 12, 2023 at 10:49PM

Show HN: Pho – Phonetic Alphabet Renderer in Rust https://ift.tt/5Y3CubZ

Show HN: Pho – Phonetic Alphabet Renderer in Rust https://ift.tt/hwSu5vK August 12, 2023 at 04:11PM

Show HN: Open-source proxy server for Llama2, GPT-4, Claude2 with Logging,Cache https://ift.tt/HGLdN0K

Show HN: Open-source proxy server for Llama2, GPT-4, Claude2 with Logging,Cache Hello hacker news, I’m the maintainer of liteLLM() - package to simplify input/output to OpenAI, Azure, Cohere, Anthropic, Hugging face API Endpoints: https://ift.tt/mvryYH5 We’re open sourcing our implementation of liteLLM proxy: https://ift.tt/mu5TZhY... TLDR: It has one API endpoint /chat/completions and standardizes input/output for 50+ LLM models + handles logging, error tracking, caching, streaming What can liteLLM proxy do? - It’s a central place to manage all LLM provider integrations - Consistent Input/Output Format - Call all models using the OpenAI format: completion(model, messages) - Text responses will always be available at ['choices'][0]['message']['content'] - Error Handling Using Model Fallbacks (if GPT-4 fails, try llama2) - Logging - Log Requests, Responses and Errors to Supabase, Posthog, Mixpanel, Sentry, Helicone - Token Usage & Spend - Track Input + Completion tokens used + Spend/model - Caching - Implementation of Semantic Caching - Streaming & Async Support - Return generators to stream text responses You can deploy liteLLM to your own infrastructure using Railway, GCP, AWS, Azure Happy completion() ! https://ift.tt/HJF5paP August 12, 2023 at 07:08AM

Show HN: Weaviate – Multi Tenancy Notebook https://ift.tt/JW5A0w6

Show HN: Weaviate – Multi Tenancy Notebook https://ift.tt/q2EySJ1 August 12, 2023 at 05:50AM

Show HN: Clop – optimise screenshots and recordings automatically https://ift.tt/EQwG84F

Show HN: Clop – optimise screenshots and recordings automatically https://ift.tt/VKa28p6 August 12, 2023 at 03:11AM

Show HN: Covert – Rewrite of HashiCorp Vault Using Rust, SQLite and Litestream https://ift.tt/ZU7lNzT

Show HN: Covert – Rewrite of HashiCorp Vault Using Rust, SQLite and Litestream https://ift.tt/AgsxaNf August 11, 2023 at 10:46PM

Show HN: A DIY airgapped, e-ink TOTP device https://ift.tt/E8gFBbt

Show HN: A DIY airgapped, e-ink TOTP device https://ift.tt/d4kMSls August 11, 2023 at 11:50PM

Show HN: VectorFlow – Open-Source Vector Embedding Pipeline https://ift.tt/L0aseMO

Show HN: VectorFlow – Open-Source Vector Embedding Pipeline Hey HN We've just released the initial version of our open-source vector embedding pipeline. It's designed to embed large volumes of data. While embedding a few documents for Q&A is straightforward, consistently ingesting gigabytes of unstructured data is a whole different ballgame. By using our API, you can embed raw data and store vectors in your vector database, sidestepping the complexities of cloud infrastructure. Now, in true YC spirit, we're launching before everything is polished. Our Github repo ( https://ift.tt/H8ZTG1M ) is a work in progress, and we're eager to get it in front of the community early on. Check out our Github repo and let us know what you think. Your feedback, suggestions, and critiques will be highly appreciated as we continue to refine and develop. https://ift.tt/H8ZTG1M August 11, 2023 at 12:35AM

Show HN: Q&A with AI Trained on Bankruptcy Law https://ift.tt/O4CMkvt

Show HN: Q&A with AI Trained on Bankruptcy Law I crawled a #$%^ ton of bankruptcy case law and pointed a LLM at it to answer bankruptcy legal questions. I just tried it on the Supreme Court's request today in its order stopping the Purdue Pharma settlement[1], and it gives a decent answer. > The parties are directed to brief and argue the > following question: Whether the Bankruptcy Code authorizes a > court to approve, as part of a plan of reorganization under > Chapter 11 of the Bankruptcy Code, a release that extinguishes > claims held by nondebtors against nondebtor third parties, > without the claimants’ consent. ChatLaw's answer: The Bankruptcy Code does not explicitly authorize a court to approve, as part of a plan of reorganization under Chapter 11, a release that extinguishes claims held by non-debtors against non-debtor third parties, without the claimants’ consent. However, courts have interpreted certain provisions of the Bankruptcy Code to permit such non-consensual third-party releases under certain circumstances. The relevant provisions of the Bankruptcy Code include Section 105(a), which empowers the court to issue any order, process, or judgment that is necessary or appropriate to carry out the provisions of this title, and Section 1123(b)(6), which allows a plan to include any other appropriate provision not inconsistent with the applicable provisions of this title. In the case of In re: Mallinckrodt PLC, (District of Delaware, 02/08/2022), the court noted that while Section 524(e) of the Bankruptcy Code should be read to preclude non-debtor releases, releases are not the equivalent of a discharge. The court also noted that the Third Circuit has recognized that bankruptcy courts do have statutory and constitutional authority to approve a plan of reorganization that contains non-consensual third-party releases, albeit, only in extraordinary cases. In the case of In Re: 18-13374-mew Aegean Marine Petroleum Network Inc. (Southern District ofNew York, 2019-04-08), the court noted that some Circuit Courts of Appeal have held that bankruptcy courts lack the power to grant nonconsensual third-party releases of the kind that the Debtors seek here. However, other Courts of Appeal, including the Second Circuit Court of Appeals, have held that bankruptcy courts have the power to impose involuntary releases, but that such involuntary releases should be imposed only in rare cases. In the case of 22-110 In re: Purdue Pharma L.P. (Second Circuit Court of Appeals, 5/30/2023), the court concluded that two sections of the Bankruptcy Code, 11 U.S.C. 105(a), 1123(b)(6), jointly provide the statutory basis for the bankruptcy courts authority to approve a plan that includes nonconsensual releases of third-party claims against non-debtors. The court further held that the bankruptcy courts inclusion of the releases is equitable and appropriate under the specific factual circumstances of this case. In the same case, in a concurring opinion, Judge Richard C. Wesley agreed that a bankruptcy court has the authority to approve a Chapter 11 reorganization plan that includes nonconsensual nondebtor releases, based on the court's precedent in In re Drexel Burnham Lambert Grp., Inc., 960 F.2d 285, 293 (2d Cir. 1992). However, he expressed concerns about the lack of explicit statutory basis for such releases in the Bankruptcy Code. In conclusion, while the Bankruptcy Code does not explicitly authorize non-consensual third-party releases, courts have interpreted certain provisions of the Code to permit such releases under certain circumstances. The permissibility of such releases often depends on the specific facts and circumstances of the case, and courts have cautioned that such releases should be approved only in rare cases. [1] https://ift.tt/QT9Oewj... https://www.chatlaw.us August 11, 2023 at 06:58AM

Show HN: Fully isolated honeypot SSH server using thrussh https://ift.tt/YSh2VJ4

Show HN: Fully isolated honeypot SSH server using thrussh https://ift.tt/qTQXiPb August 11, 2023 at 04:20AM

Show HN: Computer Socialism https://ift.tt/er5vAF7

Show HN: Computer Socialism https://chernikov.xyz/computer-socialism August 10, 2023 at 05:13PM

Show HN: Easiest way to convert PDF tables to Excel https://ift.tt/g84iPxW

Show HN: Easiest way to convert PDF tables to Excel We built a Windows app to convert PDF tables to Excel. You just have to take a screenshot of the table. Why try another app when there's so many PDF to Excel converters? It is: - Faster - More convenient - More accurate than other converters (including Excel's Power Query). Feel free to test it with complex tables (like the ones found in financial documents). https://table2xl.com August 10, 2023 at 07:35AM

Show HN: Remindme – A tool to set short-term reminders from the terminal https://ift.tt/qLGgZCn

Show HN: Remindme – A tool to set short-term reminders from the terminal Hello there! The idea behind this CLI tool is to use it for short-term reminders, e.g. to remind you (via OS-specific notifications) to do something in 2 hours or in 10 minutes. The app is supposed to be cross-platform compatible. Still, I have limited access to platforms, so it was tested only on MacOS, Ubuntu (via VirtualBox), Fedora (via VirtualBox) and Windows 10 Home. I'd appreciate any feedback on how it works on these and other OS-es. Also, I have never tested it outside my time zone (GMT+2), so it would be nice to hear from folks from other parts of the world. Any feedback, comments, and questions are greatly appreciated, as it's just a tool built for fun. Here is a short intro on how to use it: Once installed (via Homebrew, APT, YUM or binary), the usage is pretty simple: - to run the app: remindme start - to set a reminder in 5 minutes: remindme in --min 5 --about "Rewatch LOTR editors cut" Use `--sec` and `--hr` flags to set reminders in seconds or hours, respectively. - to set a reminder at a specific time: remindme at --time "22:20" --about "Replay Gothic video games" Use `--am` or `--pm` flags with 12-hour A.M./P.M. format time value if you from this way of setting time. - to see the list of incoming reminders: remindme list - to stop the app: remindme stop Please, check the GitHub repo README.md file to see the full list of available commands. Thanks, and have fun! https://ift.tt/k2X7tEF August 10, 2023 at 02:26AM

Show HN: Miteiru, a Japanese Immersion ElectronJS Video Player https://ift.tt/wPQg1Us

Show HN: Miteiru, a Japanese Immersion ElectronJS Video Player Hi people! It's been about 9 months and I think it's ready for people to try this. This is a Japanese learning desktop video player that is cross-platform, easy to setup, and open source. You might have come across some similar app, but this app + OpenAI's Whisper is a bomb... I'll be maintaining this app and tryna achieve all CJK supported video player. https://ift.tt/YIrMXSG August 10, 2023 at 04:20AM

Show HN: Automatically convert your GPT-3.5 prompt to Llama 2 https://ift.tt/auqTbmA

Show HN: Automatically convert your GPT-3.5 prompt to Llama 2 Hey HN! I'm working on OpenPipe, an open source prompt workshop. I wanted to share a feature we recently released: prompt translations. Prompt translations allow you to quickly convert a prompt between GPT 3.5, Llama 2, and Claude 1/2 compatible formats. The common case would be if you’re using GPT 3.5 in production and are interested in evaluating a Claude or Llama 2 model for your use case. Here's a screen recording to show how it works in our UI: https://twitter.com/OpenPipeLab/status/1687875354311180288 We’ve found a lot of our users are interested in evaluating Claude or Llama 2, but weren’t sure what changes they need to make to their prompts to get the best performance out of those models. Prompt translations make that easier. A bit more background: OpenPipe is an open-source prompt studio that lets you test your LLM prompts against scenarios from your real workloads. We currently support GPT 3.5/4, Claude 1/2, and Llama 2. The full codebase (including prompt translations) is available at https://ift.tt/tYAqOuM. If you’d prefer a managed experience, you can also sign up for our hosted version at at https://openpipe.ai/. Happy to answer any questions! August 10, 2023 at 03:17AM

Show HN: Automatic commit messages with AI copilot https://ift.tt/Fo5aRVt

Show HN: Automatic commit messages with AI copilot https://ift.tt/nWrIDmC August 10, 2023 at 02:22AM

Show HN: All-you-need OSS lib for modeling and working with ASTs in Python https://ift.tt/IWD5GHi

Show HN: All-you-need OSS lib for modeling and working with ASTs in Python https://ift.tt/FDJ07G8 August 9, 2023 at 04:49AM

Show HN: Subscription-Based Alternative to Gumroad https://ift.tt/uBpcO60

Show HN: Subscription-Based Alternative to Gumroad https://turbolink.io August 9, 2023 at 04:44AM

Show HN: Ggml.js – Serverless AI Inference on Browser with Web Assembly https://ift.tt/5i4qm1y

Show HN: Ggml.js – Serverless AI Inference on Browser with Web Assembly What is ggml.js? Run any ggml ported ML models directly on your web browser with ggml.js This project provides JavaScript bindings on ggml models, so that you can embed GGML models to your web apps to build serverless AI inferencing. Currently the framework supports following model types: - Dolly v2 - GPT2 - GPT J - GPT NEO X - MPT - Replit - StarCoder You can find more details about the framework: https://ift.tt/3fPHCdF For live demo examples, you can visit here: https://ift.tt/SEQ4hRF Source Code: https://ift.tt/IGe5E9Z Please do provide any feedback/questions/suggestions in the comments. I'll be happy to take it up :) https://ift.tt/3fPHCdF August 9, 2023 at 02:20AM

Show HN: Agentflow – Run Complex LLM Workflows from Simple JSON https://ift.tt/uKAiXqI

Show HN: Agentflow – Run Complex LLM Workflows from Simple JSON So, it feels like this should exist. But I couldn't find it. So I tried to build it. Agentflow lets you run complex LLM workflows from a simple JSON file. This can be as little as a list of tasks. Tasks can include variables, so you can reuse workflows for different outputs by providing different variable values. They can also include custom functions, so you can go beyond text generation to do anything you want to write a function for. Someone might say: "Why not just use ChatGPT?" Among other reasons, I'd say that you can't template a workflow with ChatGPT, trigger it with different variable values, easily add in custom functions, or force the use of custom functions for steps in the workflow. Someone might also say: "Then why not use Auto-GPT or BabyAGI?" Among other reasons, I'd say you can't if you want consistency because these tools operate autonomously, creating and executing their own tasks. Agentflow, on the other and, lets you define a step-by-step workflow to give you more control. I'd like to do more with this, including adding more custom functions, and more examples, and more ways to trigger workflows (such as in response to events). But first, I want to make sure I'm not wasting my time! For starters, if something like this already exists, please tell me. https://ift.tt/kc3gQh8 August 9, 2023 at 12:57AM

Show HN: A C++11 Hierarchical State Machine Library https://ift.tt/7Y4FcQB

Show HN: A C++11 Hierarchical State Machine Library https://ift.tt/m6klL9a August 9, 2023 at 12:15AM

Show HN: LampBuilder – Create a startup landing page in seconds https://ift.tt/jKBD3Ld

Show HN: LampBuilder – Create a startup landing page in seconds We got inspired to create a landing page builder to help us test startup ideas. Our goal is to build tools to help you quickly validate a concept and engage with potential users. LampBuilder is a free and fast landing page generator that aims to become a go-to tool for kick starting new ideas. We plan to keep the landing page generator and custom domain hosting free forever. Future plans are to add more components, a code base download option, waitlist functionality, pre-order payments/subscriptions and to expand into a MVP product builder. It will be great to hear your feedback on what tool-set would best help you validate your startup ideas. https://ift.tt/8RuBaFl August 8, 2023 at 11:16PM

Show HN: Ready to Send – a Gmail add-on that automatically drafts email replies https://ift.tt/9rEMsyL

Show HN: Ready to Send – a Gmail add-on that automatically drafts email replies Hi HN! Ready to Send works seamlessly with Gmail, crafting draft responses for your new, unread emails. You can add personalized info for each contact, ensuring every message sounds genuine. LMK your feedback below! https://ift.tt/82cM13i August 8, 2023 at 08:19AM

Show HN: An AI Textbook https://ift.tt/MCa0tXP

Show HN: An AI Textbook Hi HN, Introducing Inquistory, the world's first AI textbook for history. Unlike a textbook, students don’t passively read through long chapters of content. Inquistory briefly explains a high level ideas a student, and student's must inquire about the content to advance. Like a textbook, Inquistory utilizes both primary and secondary sources create content. This involves displaying relevant images inline with text and providing citations for the sources referenced. Read the wild story how we got started: https://ift.tt/mx7E1cT Currently in private beta, you can sign up on our website: https://inquistory.com/ https://inquistory.com/ August 8, 2023 at 04:40AM

Show HN: Create your perfect profile picture using AI https://ift.tt/gzeiL5S

Show HN: Create your perfect profile picture using AI #1 Best AI Profile Picture Generator Create your perfect profile picture in less than 10 minutes with our AI photographer! Upload 5 pictures and get 30 photos in various styles in minutes! https://ift.tt/uEfCwQy August 8, 2023 at 04:02AM

Show HN: Doculite – Use SQLite as a Document Database https://ift.tt/gpV7EBJ

Show HN: Doculite – Use SQLite as a Document Database Hi! 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. Reasons: 1) Using an SQL Database meant having less flexibility and iterating slower. 2) Alternative, proven Document Databases only offered client/server support. 3) No network. Having SQLite server-side next to the application is extremely fast. 4) Replicating Firestore's API makes it easy to use. 5) Listeners and real-time updates enhance UX greatly. 6) SQLite is a proven, stable, and well-liked standard. And, apparently one of the most deployed software modules right now. (src: https://ift.tt/DpKZfRn ) What do you think? Feel free to comment with questions, remarks, and thoughts. Happy to hear them. Thanks https://ift.tt/Eqh3KNH August 8, 2023 at 03:14AM

Show HN: Medical LLM API on par with Google Med-PaLM 2. 92% USMLE accuracy https://ift.tt/oZk7PnB

Show HN: Medical LLM API on par with Google Med-PaLM 2. 92% USMLE accuracy Hello HN! I’d like to share a medical question-answering API which has state-of-the-art performance on the USMLE self-assessment exam. You can try out the MediSearch API in 10 seconds in this Colab [ https://ift.tt/f2zpxer ], or test the search engine live at MediSearch [ https://medisearch.io ]. See our API page [ https://ift.tt/SVlf0qu ] to apply for access. Some technical highlights: 1. State-of-the-art accuracy of 92% on the USMLE self-assessment exam [ https://ift.tt/ULhTMza ]. 2. Ranked 2nd on MedQA benchmark, closely tailing Google's Med-PaLM 2 (within ~2%). 3. The API provides article references as an output. We’d love to hear feedback from this community! We’ve seen people use the MediSearch API to implement a chat bot or search field within their app. Please note that MediSearch does not have a 100% accuracy. Therefore, a human professional should always make a final decision on the information suggested by MediSearch. You can use the MediSearch API similarly to the OpenAI API [ https://ift.tt/nGNgxQK ]. If you’d like access to the MediSearch API, please email michal@medisearch.io or visit our API page [ https://ift.tt/SVlf0qu ]. Please specify your use case in the application. https://ift.tt/SVlf0qu August 8, 2023 at 12:52AM