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

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/8xCNgQj --- 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/1pfOtFL https://airfeed.co/ April 13, 2023 at 03:22AM

Show HN: GPT-4-powered web searches for developers https://ift.tt/xdJo27W

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/BJx5Pip... ) while Phind in default mode meanders a bit and answers the question very generally ( https://ift.tt/73y0bjr... ). 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/gWqivlI... ). 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

Show HN: Word Dose – Language learning on lock screen and practice with ChatCPT https://ift.tt/LIaDiA5

Show HN: Word Dose – Language learning on lock screen and practice with ChatCPT https://ift.tt/PtZ0NDV April 12, 2023 at 01:13AM

Show HN: Discord Time formatting with natural language processing https://ift.tt/LQHdwR8

Show HN: WallStreetGPT:ChatGPT plugin for connecting to brokerage and trading https://ift.tt/9p7XWRo

Show HN: WallStreetGPT:ChatGPT plugin for connecting to brokerage and trading ChatGPT Plugins are in developer alpha, but thought to share one. WallStreetGPT allows you to: 1) Fetch real time quotes (crypto or stocks) 2) Get analytics 3) Do portfolio optimization (Markowitz, etc) 4) Submit live orders (yes.. but need a brokerage account that has API connectivity like IB or Alpaca) https://twitter.com/nextworddev/status/1645814196670529538 April 12, 2023 at 12:19AM

Show HN: GPT–LLM native macOS app with time travel, versioning, search https://ift.tt/9oYTdS2

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: Foldie - Transfer Files Between Android and Mac (written in Flutter) https://ift.tt/8o453LH

Show HN: Foldie - Transfer Files Between Android and Mac (written in Flutter) https://ift.tt/0wn6RTz April 11, 2023 at 04:47PM