4 News Express

Wednesday, April 12, 2023

Show HN: Let's find Pokémon that are the same height and weight as you https://ift.tt/4ae39km

Show HN: Let's find Pokémon that are the same height and weight as you https://ift.tt/pntJH3e April 13, 2023 at 05:51AM

Show HN: Twitter API Reverse Engineered https://ift.tt/G8WwYEZ

Show HN: Twitter API Reverse Engineered endpoints: /graphql /1.1 /2 /i https://ift.tt/PNHXOJR April 13, 2023 at 05:20AM

Show HN: I’m building an autonomous business run by ChatGPT https://ift.tt/lNzoQ04

Show HN: I’m building an autonomous business run by ChatGPT Hey HN!! I just shipped a project called Airfeed: https://airfeed.co/ Here's how it works: 1. You tell it the research topics you're interested in following This can be anything -- LLMs, chatbots, image generation, scaling model inference, small language models, datasets, etc. 2. Every morning, it filters new AI research papers for quality work that is relevant to your configured topics, and sends you an email summary. Here's a sample email: https://ift.tt/nxPNYaS --- As a fun experiment, I've made everything completely autonomous: Every morning, ChatGPT takes care of filtering/processing all research papers & writing each email. --- Why I built this: I think there needs to be a better way for engineers, researchers, and AI product builders to stay up to date on the latest AI research that's relevant to whatever they're working on. For someone building LLMs, this could mean keeping up with research papers covering multiple topics, ex: scaling attention, model architecture, new datasets, new fine-tuning techniques, etc. --- How this is different from other newsletters: This isn't a generic AI newsletter. It's research-focused & personalized, since it only highlights the papers that might be relevant to you (based on your specific topics). I found this to be useful, since a lot of papers are irrelevant and/or low quality. --- When building maroofy.com [1], I would regularly read the latest research papers on everything related to: contrastive learning, vector embeddings, music classification, etc. So, I thought it would be nice to build something that filters/summarizes just the new research papers covering topics I care about, and sends me the top ones in a daily, morning email. Would love any feedback!! :D [1] https://ift.tt/XIl9g05 https://airfeed.co/ April 13, 2023 at 03:22AM

Show HN: GPT-4-powered web searches for developers https://ift.tt/h2sEkx9

Show HN: GPT-4-powered web searches for developers Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations ( https://ift.tt/Mn2i4hd... ) while Phind in default mode meanders a bit and answers the question very generally ( https://ift.tt/pR2Ccro... ). GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not. We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail. For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: ( https://ift.tt/WN5XjIQ... ). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp. We still have a long way to go and would love to hear your feedback. https://www.phind.com April 12, 2023 at 11:14PM

Tuesday, April 11, 2023

Show HN: Automatically Generate Company Names with Available Domains https://ift.tt/8piXSG7

Show HN: Automatically Generate Company Names with Available Domains I have found myself running into the issue where I think of a great project or company name, but the domain is already taken multiple times. I decided to create this simple project which uses openai and route53 (hence the name) to generate available domains for a company based on keywords, rather than just come up with new company names. https://53names.com April 12, 2023 at 01:46AM

Show HN: Discord Time formatting with natural language processing https://ift.tt/FnyI3Mg

Show HN: GPT–LLM native macOS app with time travel, versioning, search https://ift.tt/Ghvck3s

Show HN: GPT–LLM native macOS app with time travel, versioning, search Hey everyone! I made a Mac app for exploring large language models. It’s fast, small, has a tiny memory footprint. It’s immutable by design with both immediate time travel and automatic versioning as foundational elements. The app is written in Swift and a bit of Rust for the tokenizer. I used SwiftUI for structure and animations and Cocoa for advanced behavior. All storage is SQLite and local-only. You can go through the database as needed and backup it as well. The app has support for variants, which is the `n` parameter in the OpenAI chat completion API—equivalent to the drafts feature in Bard. It shows model- and ChatML-aware tokens and cost, and it dynamically adjusts response length in function of prompt length and context length. It supports hiding runs that are not useful, marking the ones that are notable, and going through the ancestry of the current run. It also has support for examples, as specified in ChatML, conversation names and personal and local-only notes. The full-text search works across all stored text and it has support for `all`, `any`, `prefix` and `phrase` matching; the results are time-ordered rather than ranked for the time being. There are several shortcuts and more are coming so that the app can be used entirely by keyboard. You can export to JSON and all data is exported. The app is sandboxed and notarized. The API keys are stored securely in the Keychain. Next I plan to implement combinatorial runs (mixing multiple values of the same parameter and multiple models as well) and full Markdown support. Currently only OpenAI’s conversational models are supported (GPT 3.5, GPT 4 8K, GPT 4 32K), but I’ll be adding support for local models and custom ChatML endpoints as soon as possible. Give it a try. Any and all feedback welcome! Thoughts and questions as well! William https://thellm.app April 11, 2023 at 11:34PM

Show HN: Profile Writer for Dating Apps https://ift.tt/rIMlvje

Show HN: Profile Writer for Dating Apps Hi folks. We built a fun app that asks a few questions and spins them into a dating app profile. Would love to hear what you think. https://ift.tt/fw8HR2i April 11, 2023 at 08:56PM

Show HN: Local-first secret manager for developers https://ift.tt/Dda1mlS

Show HN: Local-first secret manager for developers https://ift.tt/eWv8SHO April 11, 2023 at 08:45PM

Show HN: Sheet Markup – add spreadsheets to a Markdown document https://ift.tt/8k3AUE4

Show HN: Sheet Markup – add spreadsheets to a Markdown document GitHub: https://ift.tt/EoTqstf https://ift.tt/yk4ZeT7 April 11, 2023 at 06:02PM

Show HN: Rust Guideposts – 100+ topics to help learn about Rust https://ift.tt/iE0daYK

Show HN: Rust Guideposts – 100+ topics to help learn about Rust I'm teaching Rust to compsci students and recent grads who are joining tech teams. I'm creating a guide of many Rust topics and their summaries. https://ift.tt/x5ZFEap The guide is free and open source. I'm seeking ideas for improvements, to help newcomers to Rust and its ecosystem. In addition to the repo, the guide is available as an ebook PDF, with pay-what-you-wish pricing. https://ift.tt/QzSldE0 My goal is to help many people learn about Rust, so I greatly appreciate your advice and you sharing the guide if you wish. Thanks! April 11, 2023 at 12:47PM

Show HN: Skip the SSO Tax, access your user data with OSS https://ift.tt/xPW6QA1

Show HN: Skip the SSO Tax, access your user data with OSS As the former CTO of an Insurtech and Fintech startup I always had the “pleasure” to keep regulators and auditors happy. Think of documenting who has access to what, quarterly access reviews, yearly audits and so on… Like many others we couldn’t justify the Enterprise-plan for every SaaS tool to simply get access to SSO and SCIM/SAML APIs. For Notion alone the cost would have nearly doubled to $14 per user per month. That’s insane! Mostly unknown to people, SSO Tax also limits access to APIs that are used for managing user access (SCIM/SAML). This has proven to be an incredibly annoying roadblock that prevented me from doing anything useful with our user data: - You want to download the current list of users and their permissions? Forget about it! - You want to centrally assign user roles and permissions? Good luck with that! - You want to delete user accounts immediately? Yeah right, like that's ever gonna happen! It literally cost me hours to update our access matrix at the end of every quarter for our access reviews and manually assigning user accounts and permissions. I figured, there must be a better way than praying to the SaaS gods to miraculously make the SSO Tax disappear (and open up SCIM/SAML along the way). That’s why I sat down a few weeks ago and started building OpenOwl ( https://ift.tt/S0t9KQF ). It allows me to just plug in my user credentials and automatically download user lists, including permissions from SaaS tools. Granted, OpenOwl is still a work in progress, and it's not perfect. At the moment it's limited to non-SSO login flows and covers only 7 SaaS vendors. My favorite part is that you can configure integrations as “recipes”. The goal was for anybody to be able to add new integrations (IT managers and developers alike). Therefore you ideally don’t even have to write any new code, just tell OpenOwl how the new SaaS vendor works. What do you think? Have you dealt with manually maintaining a list of users and their permissions? Could this approach get us closer to overcoming parts of the SSO Tax? https://ift.tt/S0t9KQF April 11, 2023 at 06:10PM

Monday, April 10, 2023

Show HN: The Hardware Lottery https://ift.tt/2gt9wVk

Show HN: The Hardware Lottery https://ift.tt/ToiNKZY April 10, 2023 at 04:01PM

Show HN: The Coolest advancements in AI this week https://ift.tt/ED20xMh

Show HN: The Coolest advancements in AI this week I hope you find these AI breakthroughs and projects as exciting as I do! I'd love to hear your thoughts, opinions, and predictions about these advancements in the comments below. Let's have a lively discussion! I'm also excited to announce that I've started a free daily newsletter called "The AI Revolution" to help you stay updated on the latest AI advancements, all in one place. Today's post is just the first issue, and I'm completely open to suggestions for improving tomorrow's newsletter. Your feedback will be invaluable in shaping this resource. Subscribe to "The AI Revolution" and never miss an update: https://ift.tt/fsQoGgL And feel free to follow us on Twitter for more recent updates: https://twitter.com/TheAIRevolu Looking forward to your thoughts and ideas! https://ift.tt/MUbPxsd April 10, 2023 at 06:05PM

Show HN: Bridging the Gap Between Generative AI and Human Intelligence https://ift.tt/qHzWblZ

Show HN: Bridging the Gap Between Generative AI and Human Intelligence https://ift.tt/lhJOWLM April 10, 2023 at 01:08PM

Show HN: Nudge: A command line tool for sending notifications via pushover https://ift.tt/84FOtvK

Show HN: Nudge: A command line tool for sending notifications via pushover https://ift.tt/B5eAWyf April 10, 2023 at 12:57PM