Show HN: Tiger – Function Hub for LLM Agents https://ift.tt/Ldf6jWT

Show HN: Tiger – Function Hub for LLM Agents https://ift.tt/jtD8K9f April 19, 2024 at 02:58AM

Show HN: MonsterWriter – Write a thesis, post, or organize notes https://ift.tt/NszgSiX

Show HN: MonsterWriter – Write a thesis, post, or organize notes Hello HN, in 2017 I started a project that would become MonsterWriter. First envisioned as a semi-structured wiki it became a writing application specialized for scientific content. It is a perfect tool if you write your thesis. While it is focused on technical content, you can still see the knowledge management spirit in it. One or two years ago, my wife joined me in my efforts and redesigned the whole project and we recently released it as MonsterWriter2. To celebrate this milestone we are giving away free lifetime licenses for the Desktop version (till Apr 28). Just use the promo code "gu0ho4q" for a 100% discount. You can find detailed instructions here: https://ift.tt/FA8ILdh You can also find a short introduction video to the app on YouTube: https://www.youtube.com/watch?v=vR8i-EY_UBk We are happy to receive any kind of feedback! April 19, 2024 at 01:12AM

Show HN: Vapi – Convince our voice AI to give you the secret code https://ift.tt/xd79Yfi

Show HN: Vapi – Convince our voice AI to give you the secret code https://ift.tt/fjbBDCk April 18, 2024 at 10:20PM

Show HN: Minard – Generate beautiful charts with natural language https://ift.tt/OBrIaTU

Show HN: Minard – Generate beautiful charts with natural language Hi HN – Excited to share a beta for Minard, a new data visualization toolkit we've been working on that lets you generate publication-quality charts with simple natural language (throw away your matplotlib docs and rejoice!). Upload or import CSVs, Excel, and JSON, give it a spin, and please let us know what you think! (Long format data works best for now) For those curious, the stack is a simple Django app with HTMX/Alpine and all of the charts are specified and rendered as Vega ( https://ift.tt/3Id1g6q ). Lots of LLM function calling under the hood as well. https://minard.ai April 18, 2024 at 11:27PM

Show HN: I also made a three-body simulation https://ift.tt/vHwDJnI

Show HN: I also made a three-body simulation Somewhat inspired by a recent post here, I also made a three-body simulation on a whim, meaning to try out macroquad[0] (verdict: really nice!). Thanks to the engine I could trivially target wasm as well, so others can get mesmerized too. The source is available here: https://ift.tt/uWjkrD8 [0]: https://ift.tt/r89LA4S https://three-bodies.sulami.xyz/ April 18, 2024 at 06:53AM

Show HN: Trained Tiny Tales GPT(30M model)from scratch and deployed in $15 https://ift.tt/dcjRweK

Show HN: Trained Tiny Tales GPT(30M model)from scratch and deployed in $15 For the last few weeks, I have been working on training an LLM from scratch and deploying it in production on Google Cloud Platform. Finally, I trained a 30 million parameter model on 1 billion tokens and deployed it as a web service. You can access the LLM using this site - https://ift.tt/0aBXfI3 The following steps were taken to build Tiny Tales GPT 1. Downloaded and preprocessed 8GB of dataset using multiprocessing library. 2. Tokenized the data using byte pair encoding to create 1 billion tokens sharded in different bin files. 3. Defined a training setup and trained the model on a small version of the LLaMA model architecture with 30 million parameters. 4. The training was done using Distributed Data-Parallel on two A-100 GPUs provided by JarvisLabs.ai (they are most cost-optimized) 5. After the training is done, an inference script is created to predict the tokens from the trained model given the input context vector. 6. Developed REST-based API service using Flask framework to interact with the inference service to the end user. 7. Finally used GCP's virtual machines, instance groups, load balancers, and DNS services to deploy the service on the internet. https://ift.tt/RfqQg8z April 18, 2024 at 02:25AM

Show HN: Easy Folders – A folders based organization tool for ChatGPT and Claude https://ift.tt/urFUOYv

Show HN: Easy Folders – A folders based organization tool for ChatGPT and Claude Download for free: https://ift.tt/3bOCfNk A simple and powerful tool to organize chats in ChatGPT and Claude. ** NEW! Claude support added - Create folders and organize your chats for Claude ** ** NEW! Multi-account support added - Create folders and organize your chats for multiple ChatGPT & Claude accounts, and switch between them seamlessly. ** - Privacy focused, your data is all stored on your local machine - Create folders & sub-folders for your chats - Easy-to-use drag & drop - Colored folders - Automatic folders for Custom GPTs - Sync folders across multiple devices - Full chat history search - Bookmark important chats - Bulk delete chats - Backup & Import data - Dark & light mode support April 18, 2024 at 01:11AM