Show HN: AI Powered Markdown Editor for tech writers https://ift.tt/jBVAxUS

Show HN: AI Powered Markdown Editor for tech writers https://mdedit.ai/ July 30, 2023 at 08:20AM

Show HN: Llama2.ipynb https://ift.tt/9nAdPGQ

Show HN: Llama2.ipynb https://ift.tt/F1jXuE8 July 30, 2023 at 03:07AM

Show HN: Scribe – android dictaphone with speech recognition on device https://ift.tt/TY68LMX

Show HN: Scribe – android dictaphone with speech recognition on device Dear HN community! We are developing Scribe - dictaphone with speech recognition on device. On device means - audio is not sent to any cloud and stays on your phone, so it is private. The neural network runs right on the CPU of your smartphone. The app is free, there are no limits or fees based on transcription hours, one can transcribe 24/7 and pay only for electricity. This is actually a demo of our SDK, which we offer to businesses to embed in their applications, and it will stay always free for private users. It is like Google Recorder, but unlike Otter.ai or other transcribing apps based on Google Assistant. https://ift.tt/t9RXeG1... Some of the features: - record to wav, flac, aac and transcribe in real-time - transcribe from audio/video files - share to and from Scribe - access records and texts easily from file system Some of the possible uses: - transcribing lectures/trainings - court hearings - medical/psychological interviews - journalist interviews https://ift.tt/9oWHlwN July 29, 2023 at 07:22PM

Show HN: Gogit – Just enough Git (in Go) to push itself to GitHub https://ift.tt/B7O5bSq

Show HN: Gogit – Just enough Git (in Go) to push itself to GitHub https://ift.tt/YhrIdu7 July 30, 2023 at 02:04AM

Show HN: This blog post shows its Hacker News score https://ift.tt/57CPS4h

Show HN: This blog post shows its Hacker News score https://ift.tt/Yz9sr46 July 29, 2023 at 02:59PM

Show HN: An app to help you stay Focused https://ift.tt/8VkpizP

Show HN: An app to help you stay Focused I built this app in less than 4 hours over a busy and noisy weekend to help me stay focused while studying, during my college days. Since then I have been maintaining this open source project. Its been quite a fruitful and enjoyable ride. Hope you all like it :) https://ift.tt/yPnfSro July 29, 2023 at 12:08PM

Show HN: Heimdall ML - Democratizing access to machine learning https://ift.tt/gnts1BG

Show HN: Heimdall ML - Democratizing access to machine learning https://ift.tt/o0kyw4H July 29, 2023 at 02:52AM

Show HN: Worst programming language written in less than an hour https://ift.tt/CklpWhU

Show HN: Worst programming language written in less than an hour Unfinished side project inspared by JavaScript It's just a stupid interpeter for my poor language https://ift.tt/3VCn2bX July 29, 2023 at 01:32AM

Show HN: Rubbrband – Evaluating generated images at scale https://ift.tt/WD0kNgb

Show HN: Rubbrband – Evaluating generated images at scale Hey HN! We’re the founders of Rubbrband ( https://ift.tt/GNoJ1pU ), a evaluation platform for image generation models like Stable Diffusion. We provide a monitoring application to detect deformed human features in AI generated images at scale. For example, we automatically flag images of people with deformed eyes or hands. We’ve worked with several companies leveraging generative image models in production, and found that one of the main problems is that it’s hard to filter images for good quality sample at scale. Typically, teams will have to manually look through the images for these samples, which is slow and expensive. We wanted to build a monitoring solution that lets you to see all of the images you’ve generated, and to automatically be alerted when an image was generated with a deformity. We’ve started by building evaluators that detects deformities in human features, like face and hands. We’re focused on expanding rapidly into build evaluators for other types of images, like gaming and design assets. We charge using a storage-based pricing model. Rubbrband costs 5¢ per image to use, with your first 1000 images uploaded free. We’d love to hear your thoughts and critiques, if you have any feature requests please let us know! July 28, 2023 at 11:07PM

Show HN: Diffusion Models for Greeting Cards https://ift.tt/kydIrfZ

Show HN: Diffusion Models for Greeting Cards https://yoohoo.cards July 29, 2023 at 12:04AM

Show HN: Trout – relay webhook events and listen to them locally https://ift.tt/biy6sQS

Show HN: Trout – relay webhook events and listen to them locally Today, the apps we build use a LOT of APIs, including Stripe for payments, Clerk for auth, Twilio for messaging and more. But receiving these webhook events to keep our own data synchronized has traditionally been a big hassle. The problem applies to both prod and dev. In prod, we need a reliable way to subscribe to these events and deliver them to their eventual destination. In dev, we need a way to test against these events locally. The existing products in this space include ngrok, HookDeck, Convoy and others. They are all great, but they have some caveats. For one, ngrok doesn't provide stable URLs for webhook development unless you fork over money for a paid plan. For an indie/hobbyist developer just trying to test their app, this can be a non-starter. Meanwhile, HookDeck and Convoy are full-fledged webhook relays which can be complicated to use. Trout is a simpler way to do webhook development. You can create sources and plug them into your external services e.g. Stripe. Then, you can forward these events anywhere. Trout also comes with a CLI you can install and use to listen to events on any source. This makes developing on localhost easy. All feedback is welcome! https://trout.run July 28, 2023 at 11:39AM

Show HN: Envoy playground in the browser https://ift.tt/IAg9M5B

Show HN: Envoy playground in the browser Hey HN, We made an Envoy Proxy playground [0] so we could test out our Envoy configs directly in the browser. This is based on Julia's work with Nginx Playround. [1] We forked that repo and added more Envoy to it. [2] Check it out! [0] - Envoy is a popular programmable proxy similar to Nginx or HAProxy that is popular with cloud-native setups: https://ift.tt/tLEGKni [1] - https://ift.tt/yZNphKO [2] - https://ift.tt/qj6gw0y https://ift.tt/scbIDMZ July 28, 2023 at 01:29AM

Show HN: Diablo 2 runeword calculator in C++ using wxWidgets https://ift.tt/MZazCFQ

Show HN: Diablo 2 runeword calculator in C++ using wxWidgets I have programmed this a few years ago and I use it while playing. I decided to publish it because it might be useful to others. Feel free to give feedback! I am also interested in people who have used QT and wxWidgets, because I have never really used QT and would like to know about pros and cons of QT vs wxWidgets! https://ift.tt/K85U2vl July 28, 2023 at 04:16AM

Show HN: I built a Chrome extension that detects logical fallacies using GPT-4 https://ift.tt/6WbSCnu

Show HN: I built a Chrome extension that detects logical fallacies using GPT-4 Code base is here https://ift.tt/dVnJcYI Screenshots and learnings in tweet https://twitter.com/clairefroe/status/1684692302843838464?t=... I experimented with a "Bring your own API Key" approach that I think is sufficiently secure. I'll Venmo $50 to whoever can hack my OpenAI API key https://twitter.com/clairefroe/status/1684692302843838464 July 28, 2023 at 04:30AM

Show HN: lilo, A CLI to download GCP logs to a SQLite db https://ift.tt/4lAP12d

Show HN: lilo, A CLI to download GCP logs to a SQLite db https://ift.tt/nacN6le https://ift.tt/nacN6le July 28, 2023 at 01:58AM

Show HN: Emaction – GitHub styled emoji reaction for blogs https://ift.tt/hWvab8y

Show HN: Emaction – GitHub styled emoji reaction for blogs Just For Fun. https://ift.tt/GFUpgMl July 27, 2023 at 08:20AM

Show HN: Litellm – simple library to standardize OpenAI, Cohere, Azure LLM I/O https://ift.tt/L4vAMtz

Show HN: Litellm – simple library to standardize OpenAI, Cohere, Azure LLM I/O I built this library because langchain was too bloated and I needed a simple abstraction to call multiple LLM APIs. litellm has two functions - completion(), embedding() https://ift.tt/1Akub6q July 27, 2023 at 07:01AM

Show HN: The place to learn any topic, quickly https://ift.tt/Km42QXg

Show HN: The place to learn any topic, quickly Hi HN, we’re building deriveit.org, the website where you can learn any topic, quickly. On our website, you pay to ask any physics, computer science, or math question, and our community competes to give you the best explanation (for a cash reward). Right now, resources with high quality content are a time drain (papers, textbooks, and courses). We think that material is typically written in an unnecessarily hard-to-read way, but that there are tons of people who are passionate about explaining it well to others. We want to give the world access to those people, and remove barriers for them to answer questions and write content. I'm writing to encourage you to try us out, if you’re interested - ask a question on a topic you always wanted to learn (we added a free mode so you don't have to pay or sign in), and we’ll give you a condensed, easy-to-read explanation. Or write about the intuitions that you have, which you know you won’t find anywhere else online. We’re obviously in the early stages, and are very open to feedback. https://ift.tt/JSD296t July 27, 2023 at 05:27AM

Show HN: Interactive and lightweight map of NYC's Restaurant Week https://ift.tt/63jCKIs

Show HN: Interactive and lightweight map of NYC's Restaurant Week I found the official website https://ift.tt/NJnk5cI slow and tedious to navigate, so I hacked together a fast, filterable map to showcase the participating NYC restaurants during Restaurant Week. It's in pure HTML, CSS, and JS, and it uses Leaflet for mapping and a utility JS file for the searchable multi-select input. If you're interested, check out the unminified source code by right-clicking and selecting "view source". The full source is available here: https://ift.tt/GjRlgJu . https://nyc.jimoapp.com July 27, 2023 at 01:04AM

Show HN: Continue (YC S23) – Open-source coding autopilot https://ift.tt/PnvFWaE

Show HN: Continue (YC S23) – Open-source coding autopilot Hi HN, we’re Nate and Ty, co-founders of Continue, an open-source autopilot for software development built to be deeply customizable and continuously learn from development data. It consists of an extended language server and (to start) a VS Code extension. Our GitHub is https://ift.tt/FElIWnC . You can watch a demo of Continue and download the extension at https://continue.dev — — — A growing number of developers are replacing Google + Stack Overflow with Large Language Models (LLMs) as their primary approach to get help, similar to how developers previously replaced reference manuals with Google + Stack Overflow. However, existing LLM developer tools are cumbersome black boxes. Developers are stuck copy/pasting from ChatGPT and guessing what context Copilot uses to make a suggestion. As we use these products, we expose how we build software and give implicit feedback that is used to improve their LLMs, yet we don’t benefit from this data nor get to keep it. The solution is to give developers what they need: transparency, hackability, and control . Every one of us should be able to reason about what’s going on, tinker, and have control over our own development data. This is why we created Continue. — — — At its most basic, Continue removes the need for copy/pasting from ChatGPT—instead, you collect context by highlighting and then ask questions in the sidebar or have an edit streamed directly to your editor. But Continue also provides powerful tools for managing context. For example, type ‘@issue’ to quickly reference a GitHub issue as you are prompting the LLM, ‘@README.md’ to reference such a file, or ‘@google’ to include the results of a Google search. And there’s a ton of room for further customization. Today, you can write your own - slash commands (e.g. ‘/commit’ to write a summary and commit message for staged changes, ‘/docs’ to grab the contents of a file and update documentation pages that depend on it, ‘/ticket’ to generate a full-featured ticket with relevant files and high-level instructions from a short description) - context sources (e.g. GitHub issues, Jira, local files, StackOverflow, documentation pages) - templated system message (e.g. “Always give maximally concise answers. Adhere to the following style guide whenever writing code: ”) - tools (e.g. add a file, run unit tests, build and watch for errors) - policies (e.g. define a goal-oriented agent that works in a write code, run code, read errors, fix code, repeat loop) Continue works with any LLM, including local models using ggml or open-source models hosted on your own cloud infrastructure, allowing you to remain 100% private. While OpenAI and Anthropic perform best today, we are excited to support the progress of open-source as it catches up ( https://ift.tt/VLuOAYF... ). When you use Continue, you automatically collect data on how you build software. By default, this development data is saved to `.continue/dev_data` on your local machine. When combined with the code that you ultimately commit, it can be used to improve the LLM that you or your team use (if you allow). You can read more about how development data is generated as a byproduct of LLM-aided development and why we believe that you should start collecting it now: https://ift.tt/7vBWEON... Continue has an Apache 2.0 license. We plan to make money by offering organizations a paid development data engine—a continuous feedback loop that ensures the LLMs always have fresh information and code in their preferred style. — — — We’d love for you to try out Continue and give us feedback! Let us know what you think in the comments : ) https://ift.tt/FElIWnC July 26, 2023 at 11:34PM