The best Hacker News stories from All from the past day
Latest posts:
A fridge from 70 years ago has better features than the fridge I own now
NASA mistakenly severs communication to Voyager 2
NASA mistakenly severs communication to Voyager 2
Marijuana addiction: those struggling often face skepticism
Marijuana addiction: those struggling often face skepticism
LK-99: The live online race for a room-temperature superconductor
Linux Air Combat: free, lightweight and open-source combat flight simulator
How the Rich Reap Huge Tax Breaks From Private Nonprofits
Show HN: Khoj – Chat offline with your second brain using Llama 2
Hi folks, we're Debanjum and Saba. We created Khoj as a hobby project 2+ years ago because: (1) Search on the desktop sucked; we just had keyword search on the desktop vs google for the internet; and (2) Natural language search models had become good and easy to run on consumer hardware by this point.<p>Once we made Khoj search incremental, I completely stopped using the default incremental search (C-s) in Emacs. Since then Khoj has grown to support more content types, deeper integrations and chat (using ChatGPT). With Llama 2 released last week, chat models are finally good and easy enough to use on consumer hardware for the chat with docs scenario.<p>Khoj is a desktop application to search and chat with your personal notes, documents and images. It is accessible from within Emacs, Obsidian or your Web browser. It works with org-mode, markdown, pdf, jpeg files and notion, github repositories. It is open-source and can work without internet access (e.g on a plane).<p>Our chat feature allows you to extract answers and create content from your existing knowledge base. Example: <i>"What was that book Trillian mentioned at Zaphod's birthday last week"</i>. We personally use the chat feature regularly to find links, names and addresses (especially on mobile) and collate content across multiple, messy notes. It works online or offline: you can chat without internet using Llama 2 or with internet using GPT3.5+ depending on your requirements.<p>Our search feature lets you quickly find relevant notes, documents or images using natural language. It does not use the internet. Example: Search for <i>"bought flowers at grocery store"</i> will find notes about <i>"roses at wholefoods"</i>.<p>Quickstart:<p><pre><code> pip install khoj-assistant && khoj
</code></pre>
See <a href="https://docs.khoj.dev/#/setup">https://docs.khoj.dev/#/setup</a> for detailed instructions<p>We also have desktop apps (in beta) at <a href="https://github.com/khoj-ai/khoj/releases/tag/0.10.0">https://github.com/khoj-ai/khoj/releases/tag/0.10.0</a> if you want to try them out.<p>Please do try out Khoj and let us know if it works for your use cases? <i>Looking forward to the feedback!</i>
Show HN: Khoj – Chat offline with your second brain using Llama 2
Hi folks, we're Debanjum and Saba. We created Khoj as a hobby project 2+ years ago because: (1) Search on the desktop sucked; we just had keyword search on the desktop vs google for the internet; and (2) Natural language search models had become good and easy to run on consumer hardware by this point.<p>Once we made Khoj search incremental, I completely stopped using the default incremental search (C-s) in Emacs. Since then Khoj has grown to support more content types, deeper integrations and chat (using ChatGPT). With Llama 2 released last week, chat models are finally good and easy enough to use on consumer hardware for the chat with docs scenario.<p>Khoj is a desktop application to search and chat with your personal notes, documents and images. It is accessible from within Emacs, Obsidian or your Web browser. It works with org-mode, markdown, pdf, jpeg files and notion, github repositories. It is open-source and can work without internet access (e.g on a plane).<p>Our chat feature allows you to extract answers and create content from your existing knowledge base. Example: <i>"What was that book Trillian mentioned at Zaphod's birthday last week"</i>. We personally use the chat feature regularly to find links, names and addresses (especially on mobile) and collate content across multiple, messy notes. It works online or offline: you can chat without internet using Llama 2 or with internet using GPT3.5+ depending on your requirements.<p>Our search feature lets you quickly find relevant notes, documents or images using natural language. It does not use the internet. Example: Search for <i>"bought flowers at grocery store"</i> will find notes about <i>"roses at wholefoods"</i>.<p>Quickstart:<p><pre><code> pip install khoj-assistant && khoj
</code></pre>
See <a href="https://docs.khoj.dev/#/setup">https://docs.khoj.dev/#/setup</a> for detailed instructions<p>We also have desktop apps (in beta) at <a href="https://github.com/khoj-ai/khoj/releases/tag/0.10.0">https://github.com/khoj-ai/khoj/releases/tag/0.10.0</a> if you want to try them out.<p>Please do try out Khoj and let us know if it works for your use cases? <i>Looking forward to the feedback!</i>
Scientists may have found mechanism behind cognitive decline in aging
What's up, Python? The GIL removed, a new compiler, optparse deprecated
What's up, Python? The GIL removed, a new compiler, optparse deprecated
Emacs 29.1
One week of empathy training (2019)
One week of empathy training (2019)
The Long History of Nobody Wants to Work Anymore
Show HN: San Francisco Compute – 512 H100s at <$2/hr for research and startups
Hey folks! We're Alex and Evan, and we're working on putting together a 512 H100 compute cluster for startups and researchers to train large generative models on.
- it runs at the lowest possible margins (<$2.00/hr per H100)
- designed for bursty training runs, so you can take say 128 H100s for a week
- you don’t need to commit to multiple years of compute or pay for a year upfront<p>Big labs like OpenAI and Deepmind have big clusters that support this kind of bursty allocation for their researchers, but startups so far have had to get very small clusters on very long term contracts, wait months of lead time, and try to keep them busy all the time.<p>Our goal is to make it about 10-20x cheaper to do an AI startup than it is right now. Stable Diffusion only costs about $100k to train -- in theory every YC company could get up to that scale. It's just that no cloud provider in the world will give you $100k of compute for just a couple weeks, so startups have to raise 20x that much to buy a whole year of compute.<p>Once the cluster is online, we're going to be pretty much the only option for startups to do big training runs like that on.
Show HN: San Francisco Compute – 512 H100s at <$2/hr for research and startups
Hey folks! We're Alex and Evan, and we're working on putting together a 512 H100 compute cluster for startups and researchers to train large generative models on.
- it runs at the lowest possible margins (<$2.00/hr per H100)
- designed for bursty training runs, so you can take say 128 H100s for a week
- you don’t need to commit to multiple years of compute or pay for a year upfront<p>Big labs like OpenAI and Deepmind have big clusters that support this kind of bursty allocation for their researchers, but startups so far have had to get very small clusters on very long term contracts, wait months of lead time, and try to keep them busy all the time.<p>Our goal is to make it about 10-20x cheaper to do an AI startup than it is right now. Stable Diffusion only costs about $100k to train -- in theory every YC company could get up to that scale. It's just that no cloud provider in the world will give you $100k of compute for just a couple weeks, so startups have to raise 20x that much to buy a whole year of compute.<p>Once the cluster is online, we're going to be pretty much the only option for startups to do big training runs like that on.
SpaceX punched a hole in the ionosphere