Show HN: I built an app that lets you create and chat with 3D AI characters https://ift.tt/7lzksDC

Show HN: I built an app that lets you create and chat with 3D AI characters Hello everyone! I'm excited to announce the launch of Astrocyte, a web app that allows you to create and interact with 3D AI characters. Whether it's video game heroes, anime characters, political figures, or even that obscure NPC from your favorite RPG, you can bring them to life and have a chat with them on Astrocyte! Many users have already begun crafting their own characters on Astrocyte, and the conversations have been incredibly entertaining. I would be thrilled if you could give it a try and share your honest feedback. Thank you! https://ift.tt/cSQyD2x September 15, 2023 at 09:30AM

Show HN: Python SDK for iWF – workflowAsCode API orchestration engine https://ift.tt/PVzOZh3

Show HN: Python SDK for iWF – workflowAsCode API orchestration engine Main repo(with docs/wiki/discussion): https://ift.tt/cAgMzk3 Samples: https://ift.tt/6awgtGv https://ift.tt/ycTbIdx September 15, 2023 at 01:12AM

Show HN: Nue – A React/Vue/Vite/Astro Alternative https://ift.tt/1IQLRKq

Show HN: Nue – A React/Vue/Vite/Astro Alternative Author here. I've been working on this for the past ~12 months, lately full-time. I'm releasing two things today: 1. Nue JS: https://ift.tt/8sgXBuL — A tiny (2.3kb minzipped) JavaScript library for building user interfaces. It's like React/Vue core, but there are no hooks, effects, props, or other unusual abstractions on your way. Know the basics of HTML, CSS, and JavaScript and you are good to go. Nue JS supports server-side rendering (SSR), reactive components, and "isomorphic" combinations. It takes inspiration from Vue 2.0 and Riot.js. (I'm actually the original author of Riot). 2. Nue ecosystem: https://ift.tt/yf4ECnB — This is the ultimate goal and once all the sub-projects are finished, Nue will be a serious alternative to things like Vite, Next.js, and Astro. The thing is that I'm not happy with the current state of web development, so I want to write a completely new ecosystem from scratch. I'm taking advantage of the "old" innovations like progressive enhancement, separation of concerns, and semantic web design. Benefits highlighted here: https://nuejs.org/why/ All projects will be released under the MIT license. Happy to answer any questions. https://nuejs.org September 14, 2023 at 04:41PM

Show HN: SlackRevert, a Firefox extension to revert Slack's new design https://ift.tt/15irn6O

Show HN: SlackRevert, a Firefox extension to revert Slack's new design https://ift.tt/XZn3Qkr September 15, 2023 at 04:36AM

Show HN: Image Eval – An evaluation toolkit for image generation models https://ift.tt/IkSNHB2

Show HN: Image Eval – An evaluation toolkit for image generation models https://ift.tt/4EcMS5g September 14, 2023 at 10:59PM

Show HN: A vector database with semantic SQL-like filtering https://ift.tt/hxwHjYy

Show HN: A vector database with semantic SQL-like filtering Hi HN! It’s always bothered me that there’s no real equivalent of SQL WHERE for vector content. Filtering is one of the cornerstones of a modern database — but vector DBs only support either top-k sort, which is only useful for fuzzy search, or metadata filtering, which isn’t semantic. I’ve found myself wanting all the results matching my semantic query, not just k! Aside from data analysis, it's relevant if you’re trying to do any LLM reasoning: you don’t make good decisions or reach good conclusions by considering a small subset of information. So, we’ve designed a filtering primitive on top of vectors and assembled a demo on customer reviews from Trustpilot, Yelp, App Store, etc. You can select any brand/restaurant/app, and slice the review data however you want. The filter should find all matching documents, not just the top-k. Check it out at https://ift.tt/x7DFPyX ! Not super optimized yet, and really just an exploration, but hopefully gets the point across. FAQ: - Can I try it on my own data? Sure, shoot me a message at hello [at] emberml [dot] com. - How does it work? We’ve built a custom vector-based index, and we learn a high-quality decision boundary between relevant and irrelevant vectors at query time. You can think of it as forming a few-shot classifier each time. - What’s the catch? It’s far slower and less scalable than KNN/ANN right now. But I’d rather solve quality before trying to scale up quantity; tbh I’m not satisfied with vector DB performance even at @ N=1,000. A hot take, maybe? - Why don’t you just classify the data beforehand? Unstructured data has too many degrees of freedom, so it’s hard to anticipate every search/filter a priori. Our approach is somewhat analogous to schema-on-read. https://ift.tt/42zrA1l September 14, 2023 at 11:34PM

Show HN: Note AI – use AI to summarize search results so you don't have to https://ift.tt/5PLiZJN

Show HN: Note AI – use AI to summarize search results so you don't have to https://noteai.com/ September 14, 2023 at 05:32AM