Saturday, September 30, 2023

Friday, September 29, 2023

Thursday, September 28, 2023

Wednesday, September 27, 2023

New top story on Hacker News: Show HN: Using LLMs and Embeddings to classify application errors

No comments
Show HN: Using LLMs and Embeddings to classify application errors
21 by vadman97 | 0 comments on Hacker News.
Hi Hacker News! We’re Vadim and Chris from Highlight.io [1]. We do web app monitoring and are working on using LLMs/embeddings to add new functionality to our error monitoring product. Given that there’s a lot of founders/engineers using LLMs in their products, we figured we’d share how we built the new functionality, their impact on our workflows, and how you can try it out. Our goal was to build two features: (1) tagging errors (e.g. deeming an error as “authentication error” or a “database error”); and (2) grouping similar errors together (e.g. two errors that have a different stacktrace and body, but are semantically not very different). Each of these rely heavily on comparing text across our application. After some experimentation with the OpenAI embeddings API [3], we went ahead and hosted a private model instance of thenlper/gte-large (an open-source MIT licensed model), which is a 1024-dimension model running on an Intel Ice Lake 2 vCPU machine on Hugging face [4]. Our general approach for classifying/comparing text is as follows. As each set of tokens (i.e a string) comes in, our backend makes a request to an inference endpoint and receives a 1024-dimension float vector as a response (see the code here [5]). We then store that vector using pgvector [6]. To compare any two sets for similarity, we simply look at the Euclidian distance between their respective embeddings using the ivfflat index implemented by pgvector (example code here [7]). To tag errors, we assign an error its most relevant tag from a predetermined set decided by us. For example, if we tag an error as an "authentication error" or a "database error", we can allow developers to have a starting point before inspecting an issue.(see the logic here [8]). Anecdotally, this approach seems to work very well. For example, here are two authentication errors that got tagged as “Authentication Error”: * Firebase: A network AuthError has occurred * Error retrieving user from firebase api for email verification: cannot find user from uid. We also use these error embeddings to group similar errors. To decide whether an error joins a group or starts a new one, we decide on a distance threshold (using the euclidean distance) ahead of time. An interesting thing about this approach, compared to using a text-based heuristic, is that two errors with different stack traces can still be grouped together. Here’s an example: * github.com/highlight-run/highlight/backend/worker.(*Worker).ReportStripeUsage * github.com/highlight-run/highlight/backend/private-graph/graph.(*Resolver).GetSlackChannelsFromSlack.func1 Both reported as `integration api error` as they involve the Stripe and Slack integrations respectively. The neat thing is that the LLM can use the full context of an error and match based on the most relevant details about the error. We have rolled out a first version of the error grouping logic to our cloud product [9], and there’s a demo of all the functionality at [2]. Long-term, if the HN community has other ideas of what we could build with LLM tooling in observability, we’re all ears. Let us know what you think! Links [1] https://ift.tt/yhKot93 [2] https://ift.tt/DaYezyN [3] https://ift.tt/filzenq [4] https://ift.tt/EJMcjDm [5] https://ift.tt/ZpG0Ajq... [6] https://ift.tt/s8h0lF2... [7] https://ift.tt/GAhTiHc... [8] https://ift.tt/TduK0OB... [9] https://ift.tt/bJBTMHA

Read More

Tuesday, September 26, 2023

New top story on Hacker News: Ask HN: Tips for Solopreneur?

No comments
Ask HN: Tips for Solopreneur?
57 by solo_prono | 15 comments on Hacker News.
Yo HN! I have been working on some design tools in my spare time to solve problems I've faced over and over, and I'm thinking about monetizing them. I've been to some conferences recently and talked to a lot of people who have these problems as well, and they're keen to try it out. I have collected some emails, been communicating with them a bit and even got beers with one of them recently! Here's my list of concerns: 1. It is just me - is that a red flag? Some people have asked me about my team and I told them it was just me. I got the feeling that it may have turned them off because the conversation kind of ended right there. To be fair, after that I did say that it is just me right now BUTTTTTTTT why that is okay due to my experience and work history. However, yes it is my first time doing a business. 2. How do I set appropriate milestones for me to reach? Do I think about reaching 100 customers before reaching 5 recurring customers for example? 3. I'm in a small town in PNW. Does that matter if this will be an online thing anyway? Why or when do people move to big cities like Seattle/SF/NYC/Austin etc. 4. What are some ways to do marketing? Should I even think about that before I have a few customers who are using my product consistently? 5. I've been inspired by the Startup School videos. Honestly though I'm not sure about fundraising and all these things, it seems very intimidating to me. What's the difference between those things and starting a company and slowly building it up?

Read More

Monday, September 25, 2023

Sunday, September 24, 2023

Saturday, September 23, 2023

Friday, September 22, 2023

Thursday, September 21, 2023

Wednesday, September 20, 2023

New top story on Hacker News: Show HN: Mana Pool – Market for Magic Cards

No comments
Show HN: Mana Pool – Market for Magic Cards
11 by andrewljohnson | 5 comments on Hacker News.
Hi folks. I launched my first startup on HN 15 years ago (see my profile), and I wanted to post here again now. Like my last one, this project comes from one of my life's passions. I have played Magic: The Gathering for 30 years. My co-founders and I think Magic deserves its own market, and this thinking will lead to dozens of ways to make a great app. We consider what we have an MVP, and we are all going to MagicCon this weekend in Las Vegas to walk around in our Mana Pool shirts and talk to people about the future. If HN likes the site, I would appreciate you crashing it before we head out tomorrow night! https://manapool.com/

Read More

Tuesday, September 19, 2023

Monday, September 18, 2023

Sunday, September 17, 2023

Saturday, September 16, 2023

Friday, September 15, 2023

Thursday, September 14, 2023

Wednesday, September 13, 2023

New top story on Hacker News: Show HN: Lantern – a PostgreSQL vector database for building AI applications

No comments
Show HN: Lantern – a PostgreSQL vector database for building AI applications
16 by ngalstyan4 | 4 comments on Hacker News.
We are excited to share Lantern! Lantern is a PostgreSQL vector database extension for building AI applications. Install and use our extension here: https://ift.tt/ZbkWoOR We have the most complete feature set of all the PostgreSQL vector database extensions. Our database is built on top of usearch — a state of the art implementation of HNSW, the most scalable and performant algorithm for handling vector search. There’s three key metrics we track. CREATE INDEX time, SELECT throughput, and SELECT latency. We match or outperform pgvector and pg_embedding (Neon) on all of these metrics. ** Here’s what we support today ** - Creating an AI application end to end without leaving your database (example: https://ift.tt/WPwLaoe... ) - Embedding generation for popular use cases (CLIP model, Hugging Face models, custom model) - Interoperability with pgvector's data type, so anyone using pgvector can switch to Lantern - Parallel index creation capabilities -- Support for creating the index outside of the database and inside another instance allows you to create an index without interrupting database workflows. ** Here’s what’s coming soon ** - Cloud-hosted version of Lantern - Templates and guides for building applications for different industries - Tools for generating embeddings (support for third party model API's, more local models) - Support for version control and A/B test embeddings - Autotuned index type that will choose appropriate index creation parameters - 1 byte and 2 byte vector elements, and up to 8000 dimensional vectors support ** Why we started Lantern today ** There's dozens of vector databases on the market, but no enterprise option built on top of PostgreSQL. We think it's super important to build on top of PostgreSQL - Developers know how to use PostgreSQL. - Companies already store their data on PostgreSQL. - Standalone vector databases have to rebuild all of what PostgreSQL has built for the past 30-years, including all of the optimizations on how to best store and access data. We are open source and excited to have community contributors! Looking forward to hearing your feedback!

Read More

Tuesday, September 12, 2023

Monday, September 11, 2023

New top story on Hacker News: Show HN: Loopy – share and find and music you love

No comments
Show HN: Loopy – share and find and music you love
8 by kylel95 | 0 comments on Hacker News.
Hi, I created loopy, a website to share and discover music you love. A former coworker answered an ice breaker question saying his superpower would be to know every language fluently since he travels a lot. Mine would be to hear every song I would fall in love with. I realized that I will die without hearing every song that I will fall in love with. So many of my all-time favorite songs I randomly have heard at a club, coffee shop, traveling, walking by a store, etc. There is a high chance that I would have never heard those songs. Loopy aims to fix this. You can post your all-time favorite songs. If someone else love this song, there is a chance you will too :). Here is my profile: https://loopy.fm/kyle Happy listening :) - Kyle

Read More

Sunday, September 10, 2023

New top story on Hacker News: Show HN: Erlmacs – a script to update your .emacs file for Erlang development

No comments
Show HN: Erlmacs – a script to update your .emacs file for Erlang development
5 by dlachausse | 0 comments on Hacker News.
erlmacs automatically configures and updates your .emacs file with support for the emacs mode that is included with Erlang/OTP. It frees you from having to locate the installation directory of Erlang/OTP and its bundled emacs mode. It is an escript that only depends upon Erlang/OTP and Emacs. Note: There is not much in the way of error checking at this moment, but it does make a backup of your .emacs files before any destructive operations.

Read More

Saturday, September 9, 2023

Friday, September 8, 2023

Thursday, September 7, 2023

Wednesday, September 6, 2023

Tuesday, September 5, 2023

Monday, September 4, 2023

Sunday, September 3, 2023

Saturday, September 2, 2023

New top story on Hacker News: Show HN: Modular Diffusion – A modular Python library for diffusion models

No comments
Show HN: Modular Diffusion – A modular Python library for diffusion models
6 by secularchapel | 0 comments on Hacker News.
Hello everyone! I've been working on this project for a few months as part of my thesis in Machine Learning. It's meant to be a library that provides an easy-to-use but flexible API to design and train Diffusion Models. I decided to make it because I wanted to quickly prototype a Diffusion Model but there were no good tools to do it with. I think it really can help people prototype their own Diffusion Models a lot faster and only in a few lines of code. The base idea is to have a Model class that takes different modules corresponding to the different aspects of the Diffusion Model process (noise schedule, noise type, denoising network, loss function, guidance, etc.) and allow the user to mix and match different modules to achieve different results. The library ships with a bunch of prebuilt modules and the plan is to add many more. I also made it super easy to implement your own modules, you just need to extend from one of the base classes available. Contrary to HuggingFace Diffusers, this library is focused on designing and training your own Diffusion Models rather than finetuning pretrained ones (although this is possible). I would really appreciate your feedback.

Read More

Friday, September 1, 2023

New top story on Hacker News: Show HN: An Immersive Game of Thrones Multiverse Experience

No comments
Show HN: An Immersive Game of Thrones Multiverse Experience
4 by thronesMultiV | 0 comments on Hacker News.
Alpha Version Demo: https://ift.tt/Dpkv60q Twitter: https://twitter.com/ThronesMultiV/status/1697440568874348953 We're here to present an experimental product empowered by the blend of Stable Diffusion and ChatGPT! Dive into Westeros like never before. Our experimental product offers an immersive storytelling experience where you play a pivotal role in shaping the narrative. Ever wondered if the ending of the final seasons of Game of Thrones could've been different? Now's your chance to twist the tale. Current Features : - AI-driven alternative endings starting from the end of S7. - Real-time story interventions, allowing you to change the plotline as you read. What's Next : - Continuous enhancements to refine and polish the storytelling experience. - And yes, we're contemplating open-sourcing the project – giving back to this amazing community and encouraging further innovation. We truly believe in the power of collaboration. If you have feedback, suggestions, or just want to geek out about Westeros, shoot us an email at ready2play.contact@gmail.com ! Additionally, if you're as passionate about AI and storytelling as we are, we'd love for you to collaborate with us on this exciting project. Remember, winter is coming, but with AI, the possibilities are endless. Stay excited and stay kind! Valar Morghulis!

Read More

Popular Posts

Recent Posts

Unordered List

Text Widget

Blog Archive

Search This Blog
Powered by Blogger.