Show HN: A LinkedIn Chat GPT on Steroids https://bit.ly/3Wvef0T

Show HN: A LinkedIn Chat GPT on Steroids https://bit.ly/3WvefxV December 29, 2022 at 11:25AM

Show HN: Zcached, in-memory key-value cache wire-compatible with memcached https://bit.ly/3G0m6fY

Show HN: Zcached, in-memory key-value cache wire-compatible with memcached zcached is an in-memory key-value cache exposing a memcached ASCII protocol-compatible interface, built on pluggable cache engines like Ristretto and freecache [0]. It's not performance-competitive with memcached, especially at higher thread counts. That said, it achieves about 1.1M ops/s, but at significantly higher P99 and P999 latency (as measured by memtier). See [1] and [2] for benchmark results from my 7950x-based workstation. Disclaimer: This is a hobby project created for fun while hacking over the holidays. zcached is not a commercial product and never will be. Don't use it in production; consider this a technology demo more than anything. I don't expect the source code to build outside of my environment, but for those interested in playing with it, binary artifacts are available at [3]. Try `zcached --address tcp:localhost:11211`. [0] https://bit.ly/3WQlosl , https://bit.ly/3vocwhP [1] memcached, 16 worker threads: https://bit.ly/3WQlpMV [2] zcached: https://bit.ly/3G220lg [3] https://bit.ly/3hVt263... https://bit.ly/3FXW2BX December 28, 2022 at 06:48PM

Show HN: Track Institutional Investors https://bit.ly/3Ww35cg

Show HN: Track Institutional Investors https://bit.ly/3jybFZm December 28, 2022 at 09:33PM

Show HN: Pbproxy – Send your clipboard anywhere you can ssh https://bit.ly/3G3KvkC

Show HN: Pbproxy – Send your clipboard anywhere you can ssh pbproxy is a small wrapper to give you a consistent and remotely accessible interface to your system clipboard on linux and mac. https://bit.ly/3Vrd7Kh December 28, 2022 at 10:12AM

Show HN: I built haystack – Google for the workplace https://bit.ly/3I9gTFm

Show HN: I built haystack – Google for the workplace Hi Yuval here! historicly a security researcher, more recently entered the NLP space! Iv'e started working on haystack recently because I feel modern workplaces are in dire need of a good workplace search product that is free to use just like google. Information is scattered between too many communication channels, we communicate with our peers through slack and email, share docs and specs on confluence, work with tickets on jira, commit code and have discussions on github, not to mention all the .docx, .ppt and .pdf that fly around the organization. Not to mention the fact that existing search featuers just plain suck, if you tried using confluence search you know what I mean, keyword search is terrible. Even when you find relevant looking results, they require you to commit to entering the page, and scroll through to get to the relevant paragraph. What does haystack do? - Enable you to search all your workplace applications from one place. (slack, confluence, notion, jira, github, outlook, gmail, etc...). - Natural language queries ("How to do X”, "Do we support Y", "How do I connect to Z"). - Help you decide if the result is relevant without entering the page. - Go directly: search result->relevant paragraph inside page. (no extra scrolling) - No download, all the magic happens in the browser. - Local browser storage option. (you don't need to trust me with your internal communications to use haystack). - Code references embedded in search results. Example, "How to connect to integ2 machine" on haystack could give you: ssh -i private.pem ubuntu@ec2-integration2.eu-west-1.compute.amazonwes.com aggregated from a slack communication you had a while ago. It was quite a challenge to get it up and running in the browser, but here's what I ended up using: IndexDB browser API for storage, and a fine-tuned TinyBERT-based bi-encoder for indexing, searching. Search result building involves using a fine-tuned t5-small model, there's some nodejs adaptations, and wasm rewrites in rust for performance. Next Steps fine-tuning haystack for lower-end laptops with no dedicated GPU, I'm feeling like it should be running smoothly for lowerend hardware by Feb/March, so that's the current public release date. If you would like to get early access + you have dedicated graphics, there's a button in our landing page, and my email address. I'll be here in the comment section! https://bit.ly/3hPOHg0 December 28, 2022 at 03:09PM

Show HN: Get user feedback. Make it a conversation https://bit.ly/3vnm0dq

Show HN: Get user feedback. Make it a conversation https://bit.ly/3hUkJaB December 28, 2022 at 08:57AM

Show HN: GPT Classifies HN Titles https://bit.ly/3vmEVVw

Show HN: GPT Classifies HN Titles With all the "what can GPT do", I went to dabble with it to see if I could do something that plays to its strengths rather than just speculating about "would it be good at that?" https://bit.ly/3WQ0ysW The basis for the prompt is: Classify following titles into one or more of {US Politics}, {World Politics}, {Technology}, {Security}, {Current Events}, {Boasting}, {Curiosity}, {Unknown} The results from the front page as I type this: 34152137 Technology: Lite XL: A lightweight text editor written in C and Lua 34151880 Curiosity: Hydrochloric acid is more complicated than you think 34156235 World Politics, Current Events: Apple Japan hit with $98M in back taxes for missing duty-free abuses 34152333 Technology: The Architecture of the Lisa Personal Computer (1984) [pdf] 34151951 Curiosity: The Zen anti-interpretation of quantum mechanics (2021) 34155009 Unknown: Added 49 volumes of Arkansas, Mississippi, and Tennessee law 34145665 Technology: FEA Solver that doesn't need defeaturing 34151107 World Politics, Current Events: Amazon packages burn in India, final stop in broken recycling system 34155783 Technology: Your Cellphone Will Be a Satphone 34154778 World Politics, Current Events: Vandals destroy 30k-year-old indigenous cave drawings in Australia 34146397 Boasting: Ask HN: Elevator Pitch for a Polymath? 34151708 Technology: All About USB-C: Illegal Adapters 34149340 World Politics, Current Events: Southwest cancels 5,400 flights in less than 48 hours 34154896 Technology: Beaker Browser is now archived 34145811 Technology: Run Third-Party Scripts from a Web Worker 34152978 World Politics, Current Events: When Algorithms Rule, Values Can Wither 34152981 Security: Experian Vulnerability Shows Any Report with just SSN, DOB, ADR 34151382 World Politics, Security, Current Events: US Government demands direct police access to European biometric data [pdf] 34143272 Curiosity: Archaeologists devise a better clock for Biblical times 34149804 Technology: Using eBPF and predefined inspections to minimize “observability tax” 34155875 US Politics: Ventura Issues 34152100 Technology: Anki SRS Algorithm : Spaced repetition explained with code 34154406 Technology: How RISC-V Timer Interrupts Work 34146493 Curiosity: Old-school computing: when your lab PC is ancient (2021) 34152369 Technology: BorgBackup: Deduplicating archiver with compression and encryption 34147825 Technology: Show HN: Self-hosted CMS on serverless Cloudflare 34153648 Boasting: Brooklyn Bar Menu Generator (2015) 34117429 Unknown: “Blue Light” creating capacity for nothing (2007) 34149239 Curiosity: Visually symmetric words There are certainly some that one could argue would be different though I think its fairly correct based on titles alone. I'll also note that there are some different results when I was working in a smaller sample size - the entry "Added 49 volumes of Arkansas, Mississippi, and Tennessee law" was classified as "US politics, Current Events" rather than "Unknown". I do want to note that isn't that bad. Running this: "prompt_tokens":560,"completion_tokens":222,"total_tokens":782 So, this is just a hair under $0.02 to do. Thinking about it, some cleanup can be done by removing the year and media type which could trim a few tokens off the request. December 28, 2022 at 03:00AM

Show HN: Mastinator. Disposable public anonymous no-login Fediverse accounts https://bit.ly/3I67Ncr

Show HN: Mastinator. Disposable public anonymous no-login Fediverse accounts https://bit.ly/3jsCTR3 December 28, 2022 at 02:28AM

Show HN: Merry Sky, Dark Sky replacement and merry-timeline open source lib https://bit.ly/3I5M6sM

Show HN: Merry Sky, Dark Sky replacement and merry-timeline open source lib Hello HN, This is a website I worked on during the holidays to fill the void of the upcoming dark sky shutdown. For me, the precipitation timeline was a view I was heavily relying on for everyday activities and planning. I had not found any replacement from the various weather apps. When I found pirateweather.net as a backend API, it gave me the motivation to put the pieces together and get back the experience I enjoyed. I then added more functionalities that I think was missing from the website such as a weekly chart view. I've been using the website reliably over christmas holidays. Hope you enjoy it too! Also I open sourced the visual component for drawing the precipitation timeline and you can use it for drawing weather information or any other hourly activities really https://bit.ly/3C0ASCb Interested in your feedback! https://bit.ly/3WuFNmZ December 28, 2022 at 12:14AM

Show HN: I built a simple CLI helper integrating with GPT-3 https://bit.ly/3I4M8kA

Show HN: I built a simple CLI helper integrating with GPT-3 Hi all! I don’t think CHATGPT has gone unnoticed by anyone here on Hackernews. I’ve myself played around a bit with it, but felt it was annoying to always have to log into their GUI to ask the questions. To scratch my own itch and at the same time learn more about how to write my own command line interface, I created 'askai'. 'askai' is a simple CLI integration with OpenAI’s GPT3 models. I’ve primarily used it to get quick answers to technical questions, like: > askai "How to mock user input when writing a Python pytest test?" > askai "How do I remove a conda environment?" As I've found it quite helpful, I decided to spend some time to package it in a nicer way to share it with all of you. I've also uploaded it to PyPI to simplify the installation process. 'askai' enables you to: * Ask questions and get the answers straight into your terminal * Configure which model and model parameters you want to use * Overwrite saved configurations when you ask questions Currently, it only supports OpenAI’s models, but my plan is to integrate more endpoints as soon as new capable NLP endpoints are popping up. I hope some of you find it useful :) https://bit.ly/3PSy2F3 December 27, 2022 at 05:29PM

Show HN: Sideproject.guide https://bit.ly/3C3Jnwg

Show HN: Sideproject.guide https://bit.ly/3hTH5Je December 27, 2022 at 07:36AM

Show HN: Gamedrop – Videogame collection management, price alerts, and prices https://bit.ly/3FOj4uU

Show HN: Gamedrop – Videogame collection management, price alerts, and prices https://bit.ly/3jwiVFd December 27, 2022 at 02:53AM

Show HN: How many advertising panels in Sydney are near a public telephone? https://bit.ly/3I4jiB1

Show HN: How many advertising panels in Sydney are near a public telephone? https://bit.ly/3WpyME3 December 27, 2022 at 12:57AM

Show HN: Eleven – open-source alternative to Codespaces https://bit.ly/3Glv2hp

Show HN: Eleven – open-source alternative to Codespaces Hey HN, Eleven is the second project that I've built to learn Go. It lets you create a code sandbox in your cloud provider account easily. What's a "code sandbox"? Just a VM, running in your cloud provider account, with some runtimes pre-installed, your repositories cloned, a way to connect to it with your preferred editor (or via SSH) and a way to serve your apps easily via HTTP (with automatic HTTPS). You could use it to deploy your app, as a remote development environment or even to test some code. It's up to you. For example, to deploy a Node.JS app: $ eleven aws init hello-world --runtimes node@18.7.0 --repositories eleven-sh/hello-world > Success! The sandbox "hello-world" was initialized. $ ssh eleven/hello-world forever node index.js > Forever: command started. Run "forever stop" in current path to stop. $ eleven aws serve hello-world 8000 --as hello.eleven.sh > Success! The port "8000" is now reachable at: https://bit.ly/3sYF9kp $ curl https://bit.ly/3sYF9kp > Hello World Still learning Go by the way, so I'm open to any suggestions to improve. https://bit.ly/3DspXBb December 26, 2022 at 11:27PM

Show HN: Test if your shortcut conflicts with any default shortcuts in browsers https://bit.ly/3vnbqmo

Show HN: Test if your shortcut conflicts with any default shortcuts in browsers https://bit.ly/3FW7rSR December 26, 2022 at 09:04PM

Show HN: 80/20 Rule in Everything https://bit.ly/3GgHRJI

Show HN: 80/20 Rule in Everything The content of the 8020.in website was generated using the ChatGPT AI engine and then reviewed by a human editor to ensure accuracy. https://bit.ly/3VpXDWQ December 26, 2022 at 12:29PM

Show HN: Talk to GPT-3.5 via WhatsApp https://bit.ly/3jjFlJy

Show HN: Talk to GPT-3.5 via WhatsApp https://bit.ly/3FRmn4B December 26, 2022 at 04:54AM

Show HN: Secure end-to-end client sessions and API calls using crypto key pairs https://bit.ly/3hODpZa

Show HN: Secure end-to-end client sessions and API calls using crypto key pairs Hello. I made this project as an experiment in using key cryptography for user identity in a client <-> server model, and for some future peer to peer projects that I am working on. I am looking for feedback, please let me know what you think. Also, Merry Christmas to HN! :-) https://bit.ly/3vhXhHk December 25, 2022 at 11:07PM

Show HN: Kweb 1.3.3 released, a server-side interface to the browser's DOM https://bit.ly/3POWLKt

Show HN: Kweb 1.3.3 released, a server-side interface to the browser's DOM https://bit.ly/3WLjF7t December 25, 2022 at 10:10PM

Show HN: Bespoke Artist Website Hosting https://bit.ly/3C0Ka0Q

Show HN: Bespoke Artist Website Hosting Merry Christmas everyone! We started offering hosting services for our musical artists at our record label Epsilon Records ( https://bit.ly/3C0Kb4U ) and we recently decided to open the offering further. Consider it boutique high-touch hosting at a good value for a very niche musical artist audience (bands/producers/musicians). We offer a choice of the WordPress or Ghost platform but can also handle custom requirements for the more technical customer. Get in touch and let’s nerd out over how we can help you meet your musical and artistic hosting needs. And now a word from ChatGPT: "Why choose Epsilon for your musical hosting needs? There are several reasons why you may want to choose a hosting provider that specialises in music: * Expertise: A hosting provider that specialises in music will have a deep understanding of the specific needs and requirements of music websites. This includes things like fast loading times for streaming audio and video, and the ability to handle large amounts of traffic. * Music-specific features: A hosting provider that specialises in music may offer features that are specifically tailored to the needs of music websites, such as integrations with music streaming platforms or tools for promoting and monetizing your music. * Niche-specific support: A hosting provider that specialized in music will likely have a team of support staff who are knowledgeable about the specific needs and challenges of music websites. This can be especially helpful if you have questions or run into issues specific to the music industry. Overall, choosing a hosting provider that specialized in music can help ensure that your website has the features and support it needs to succeed in the competitive world of online music." Open to feedback! https://bit.ly/3C36bMB December 25, 2022 at 09:52PM