Show HN: Lightsaber Battle – May the Fourth Be with You https://ift.tt/oazfBsj

Show HN: Lightsaber Battle – May the Fourth Be with You Hey folks, join me in a lightsaber battle! I love Star Wars and may 4th is a special day for me, so I made this little thing. You can change the saber color and background. Let me know what you guys think and May the Fourth be With You https://ift.tt/cDqJSbC May 4, 2024 at 02:01AM

Show HN: BandMatch – "Tinder" but for finding musicians to create bands/collab https://ift.tt/Pc3EIzh

Show HN: BandMatch – "Tinder" but for finding musicians to create bands/collab https://bandmatch.app May 3, 2024 at 11:41PM

Show HN: Prompt Tower – Simplify writing prompts with multiple code blocks https://ift.tt/ujZ6yFG

Show HN: Prompt Tower – Simplify writing prompts with multiple code blocks Prompt-tower simplifies and speeds-up how prompts with multiple code blocks are written. It's often a pain jumping between files, classes, functions, etc and copying/pasting everything, wrapping and annotating the blocks, and finally sending the prompt off for generation. After seeing filekitty [1], I felt inspired to build a version of the idea I’ve had for awhile now... which is a vscode extension that fits better in a developer's context. check it out: https://ift.tt/kBouIyA... demo gif: https://ift.tt/wfWLv40 repo: https://ift.tt/KUlrvMu [1] https://ift.tt/G6gOB80 May 3, 2024 at 11:40PM

Show HN: 2,629 Tiny Demos from Pouet, Running in the Browser https://ift.tt/UgwBDdN

Show HN: 2,629 Tiny Demos from Pouet, Running in the Browser https://ift.tt/cphmzfG May 3, 2024 at 02:27AM

Show HN: AI-Powered Summaries for LinkedIn Posts https://ift.tt/oh60kr3

Show HN: AI-Powered Summaries for LinkedIn Posts https://www.linkedin-tldr.xyz/ May 3, 2024 at 12:45AM

Show HN: Anonymous chat service with no registration or installation required https://ift.tt/P39qFJv

Show HN: Anonymous chat service with no registration or installation required Cannon is a chat service created to mimic physical conversions. Like in real life, there is no chat history or account setup. If you want to test the service, feel free to message me: https://ift.tt/ADN9ZbB... https://ift.tt/o05PYq7 May 2, 2024 at 11:53PM

Show HN: I created a selfhostable steam-like platform for loose game files https://ift.tt/NpsWiuy

Show HN: I created a selfhostable steam-like platform for loose game files https://gamevau.lt/ May 2, 2024 at 02:25AM

Show HN: I made an online financial modeling platform for stocks https://ift.tt/Rogij8s

Show HN: I made an online financial modeling platform for stocks https://ift.tt/CipWvbl May 2, 2024 at 01:11AM

Show HN: FileKitty – Combine and label text files for LLM prompt contexts https://ift.tt/Q1kpCfD

Show HN: FileKitty – Combine and label text files for LLM prompt contexts https://ift.tt/zlHI9eA May 1, 2024 at 11:40PM

Show HN: Cloud Seeder - Self Host with a Click on Your Home PC – Golang https://ift.tt/PAc5jJg

Show HN: Cloud Seeder - Self Host with a Click on Your Home PC – Golang https://ift.tt/WcplNsj May 1, 2024 at 05:22AM

Show HN: I built a Plant Identification Tool Powered GPT4 Vision https://ift.tt/2t0xG8n

Show HN: I built a Plant Identification Tool Powered GPT4 Vision https://ift.tt/OYUfCil April 30, 2024 at 09:53PM

Show HN: I replicated Anthropic's monosemanticity research using just my MacBook https://ift.tt/yV1ZwvC

Show HN: I replicated Anthropic's monosemanticity research using just my MacBook Hi everyone, I've been working on an open-source implementation of Anthropic's research on monosemanticity ("Towards Monosemanticity"). The problem Anthropic is trying to solve is that language models are hard to interpret because individual neurons can be responsible for multiple different things. The research finds that training a small autoencoder on neuron activations can result in "features" which are much easier to interpret. When I was reading the original research, I got really excited when I realized that the models they used were really small, and I could probably train them from scratch with just my M3 MBP. My models are somewhat undertrained compared to what Anthropic produced, but I think my results are still very compelling. Let me know what you think! https://ift.tt/ipVvkc7 April 30, 2024 at 10:56PM

Show HN: Community-written abstracts for research papers https://ift.tt/MRso07y

Show HN: Community-written abstracts for research papers https://ift.tt/4upyZDP April 30, 2024 at 11:04AM

Show HN: Define and implement any function on the fly with LLMs https://ift.tt/RsNyg1C

Show HN: Define and implement any function on the fly with LLMs It's not a serious library, but I figured it could be something fun to make. https://ift.tt/zEeBIX5 April 30, 2024 at 04:29AM

Show HN: Attorch – PyTorch's nn module written in Python using OpenAI's Triton https://ift.tt/JEX1sdO

Show HN: Attorch – PyTorch's nn module written in Python using OpenAI's Triton attorch is a subset of PyTorch's nn module, written purely in Python using OpenAI's Triton. Its goal is to be an easily hackable, self-contained, and readable collection of neural network modules whilst maintaining or improving upon the efficiency of PyTorch. In other words, it intends to be a forkable project endowed with a simple, intuitive design that can serve as an accessible starting point for those who are seeking to develop custom deep learning operations but are not satisfied with the speed of a pure PyTorch implementation and do not have the technical expertise or resources to write CUDA kernels. There already exist a number of wonderful PyTorch-like frameworks powered by Triton, but most concentrate solely on Transformers and NLP applications, whereas attorch aims to be more inclusive by also presenting a variety of layers pertaining to areas besides NLP such as computer vision. Moreover, attorch is not an inference-only package and fully supports both forward and backward passes, meaning it can be used during training as well as inference, though its performance for the latter is generally not on par with dedicated inference engines. Questions and feedback are welcome in the comments sections. https://ift.tt/tXipzgG April 30, 2024 at 01:07AM

Show HN: Kaytu – Optimizing cloud costs using actual usage data https://ift.tt/mbM8jBp

Show HN: Kaytu – Optimizing cloud costs using actual usage data Reduce your cloud costs - SREs/DevOps/Cloud Engineers Hi community! We are Kaytu (“Kay-two,” named after the K2 mountain), and we've developed an open-source tool for engineering, DevOps, and SRE teams to reduce cloud costs. Cloud inflation (“cloud-flation”) is real—AWS EC2 costs are up 23% (4-5x global inflation average [1]), and 30% of the capacity that is paid for is simply wasted ([2]). The best way to improve cloud utilization is by simplifying the process so engineers can spot inefficiencies and suggest changes. We built a simple open-source CLI tool that recommends a cost-optimal workload based on actual usage data from observability tools. Check it out at https://ift.tt/ZmAUbgL Currently, we support AWS EC2 On-Demand Servers & EBS Storage using observability data from CloudWatch to determine utilization. You can optimize EC2 Servers based on CPU, Network, Memory, and Storage. We're expanding support to include OS License, GPU metrics, RDS, and Prometheus integration, and we plan to add more AWS services like EKS and OpenSearch, as well as Azure. This is more than just a utility—we want to provide a no-nonsense platform that makes it ridiculously easy for engineers to build cost-effective apps on the cloud by optimizing workload configurations and customizing to scenarios. Open Core: Inspired by Sid Sijbrandij and GitLab, we've open-sourced our CLI and are actively working on the server side. Our tooling will always remain straightforward and support open-source tools for free. We made it as simple as possible to try out - it’s one command, no sign-up needed, no SaaS platform to share your credentials. We would love you to try it out and give us your feedback! If there are bugs, we would greatly appreciate it if you reported them on GitHub. Cheers, The Kaytu Team (Anil, Arta, Mahan, and Saleh) References: [1]Tangoe IT Trends Savings Recommendations and Liftr Insights data Cloud Pricing [2] Flexera State of Cloud Report - Multiple reports spanning 2017-2023 https://ift.tt/ZmAUbgL April 29, 2024 at 09:27PM

Show HN: See SAT sites close to you for June SAT https://ift.tt/VxsyKTB

Show HN: See SAT sites close to you for June SAT https://ift.tt/FDgCxYs April 29, 2024 at 08:37AM

Show HN: Bard PDF – Chat with Pdf in Google Bard or Gemini https://ift.tt/akhyfAv

Show HN: Bard PDF – Chat with Pdf in Google Bard or Gemini Chat with pdf in Google Bard or Gemini for free. Several ways to have conversations with pdfs in Google Bard or Gemini. https://bardpdf.dev April 29, 2024 at 08:31AM

Show HN: Dotenv, if it is a Unix utility https://ift.tt/e7cHI1a

Show HN: Dotenv, if it is a Unix utility I like the idea of using dotenv files, but I dislike having to use different language-specific libraries to read them. To solve this, I created a small utility that lets you prefix any command with "dotenv" to load the ".env" file. This is how I imagine dotenv would work if it had started as a UNIX utility rather than a Node.js library. https://ift.tt/wxABT1s April 29, 2024 at 01:55AM

Show HN: Audio Mastering with Text Prompts https://ift.tt/EycGHRi

Show HN: Audio Mastering with Text Prompts https://diktatorial.com April 28, 2024 at 11:35PM