Stuff
3 subscribers
200K links
Download Telegram
Against "Against Life Extension"
13 by quadrin | 2 comments on Hacker News.
215 Department Store Catalogs 1908-2019
3 by bookofjoe | 0 comments on Hacker News.
AGI Is Not Multimodal
14 by danielmorozoff | 5 comments on Hacker News.
FFmpeg Merges WebRTC Support
15 by Sean-Der | 0 comments on Hacker News.
Show HN: Verysmall.site – vibecode single page websites
10 by sixhobbits | 7 comments on Hacker News.
I heard you like vibe coding so I vibe coded a site where you can vibe code sites. I had non-technical relatives who needed a really simple website. I could have built it for them in a couple of hours, but instead I spent a few more hours to solve the more general problem. They want to talk to a technical person to create and make basic updates to a simple landing page. I know v0, loveable, replit etc all exist, but they still have a learning curve, and then hosting gets expensive. This way they can download the site as a single HTML file and upload it to their oldschool ISP webhosting package. I was inspired by carrd.co which I used a lot from when it was still html5up all the way through its various iterations. I think constraints can actually be good sometimes, though in this case probably the lack of way to upload images and other assets to integrate might be too much of a limitation. It's fully vibe-coded using Replit agent (which I bought on a Black Friday special and some extra credits for this month) and also hosted on Replit. I have no idea how scalable it is or how many concurrent users it can serve, or how reliable the vibe coded queue system is, but I guess I might be about to find out. Let me know what you think
Show HN: GPT image editing, but for 3D models
22 by zachdive | 4 comments on Hacker News.
Hey HN! I’m Zach one of the co-founders of Adam ( https://www.adamcad.com ). We're building AI-powered tools for CAD and 3D modeling [1]. We’ve recently been exploring a new way to bring GPT-style image editing directly into 3D model generation and are excited to showcase this in our web-app today. We’re calling it creative mode and are intrigued by the fun use cases this could create by making 3D generation more conversational! For example you can put a prompt in such as “an elephant” then follow it up by “have it ride a skateboard” and it preserves the context, identity and maintains consistency with the previous model. We believe this lends itself better to an iterative design process when prototyping creative 3D assets or models for printing. We’re offering everyone 10 free generations to start (ramping up soon!). Here’s a short video explaining how it works: https://ift.tt/yIx9NPQ We’d also love you to try our parametric mode (free!) which uses LLMs to create a conversational interface for solid modeling as touched on in a recent HN thread [2]. We are leveraging the code generation capabilities of these models to generate OpenSCAD code (an open-source script based CAD) and are surfacing the variables as sliders the user can toggle to adjust their design. We hope this can give a glimpse into what it could be like to “vibe-CAD”. We will soon be releasing our results on Will Patrick's Text to CAD eval [3] and adding B-rep compatible export! We’d love to hear what you think and where we should take this next :) [1] https://ift.tt/XKQmugr [2] https://ift.tt/IMGJSxR [3] https://ift.tt/LdmrHNp...
Doubling Down on Open Source
15 by clemo_ra | 0 comments on Hacker News.