News for hackers. Stuff that matters.

addy999

addy999 on Hacker News

Show HN: NativeBlend – Text to fully editable 3D Models that don't suck

Posted by addy999 on Monday October 20, 2025 @02:57PM
from the show-hn dept.

https://native-blend-app.vercel.app/

I'm a developer (not a 3D artist) who's been frustrated with current AI text-to-3D tools — most produce messy, monolithic meshes that are unusable without hours of cleanup.So I built NativeBlend, a side project aimed at generating editable 3D assets that actually fit into a real workflow.Key features:- Semantic Part Segmentation: Outputs separate, meaningful components (e.g., wheels, doors),...

( Read More... | 1 comment | 2 points | on HN )
Re:Building Effective Text-to-3D AI Agents: A Hybrid Architecture Appr... on Tuesday October 07, 2025 @01:07PM (#45505783)
In my testing I tried Gemini 2.5 Pro, Qwen 3 Coder 480B and Opus

I built a Context7 alternative that costs 40% less with similar code quality

Posted by addy999 on Monday September 29, 2025 @12:36PM
from the self-post dept.

I've been working on a RAG-based solution that functions similarly to Context7 but at a significantly lower cost. After some rigorous testing, I thought I'd share my findings with the community.TL;DR: This implementation costs roughly half as much as Context7 while producing code of comparable quality.The TestsI ran three coding challenges using Gemini-2.5-pro (set to temp=0) with both Context7...

( Read More... | no comments | on HN )
Re:LLMs can now generate 3D models (example) on Wednesday September 24, 2025 @01:23PM (#45363350)
Thanks to tools like Blender and MCP servers, models from Gemini to Qwen can be used to create fully usable models.

Having LLMs generate code to build a model by using tools like an artist would drastically increases quality over models produced directly by text-to-3d models like Hunyuan3d

More examples I was able to generate: https://imgur.com/a/3d-models-generated-by-ai-agent-qzOMpqr

Re:We Automated the Most Thoughtful Secret Santa in Tech History on Saturday December 14, 2024 @12:41PM (#42418367)
Oh nice! I'm building an agent like AirTop with a focus on asynchronous use: https://www.onequery.app
Re:Ask HN: Those making $500/month on side projects in 2024 – Show and... on Thursday December 12, 2024 @03:10AM (#42397260)
I'm building an AI web agent to fetch detailed information. Looks up and browses sites just like you.

Have just over 500 developers signed up and releasing our client library soon.

https://www.onequery.app

Re:Have you made Custom landing page with AI? on Tuesday November 26, 2024 @04:56PM (#42250497)
I find v0.dev is remarkably good at this. But deploying straight from there is not frictionless atm.
Re:Ask HN: How do you handle repetitive research tasks in your workflow? on Tuesday November 26, 2024 @02:49PM (#42249279)
Your approach makes a lot of sense. Especially for "old school" websites with simple Server Side rendered pages, tables are a treasure of data. Wikipedia tables would be a great use of your tool too.

I was thinking more on the lines of programmatic access that `enforces` structured output. LLMs are really good at this step. Define a schema and get an output that is guaranteed to fit.

You can see some examples of what I mean here: https://query-rho.vercel.app/

Ask HN: How do you handle repetitive research tasks in your workflow?

Posted by addy999 on Tuesday November 26, 2024 @01:53PM
from the ask-hn dept.

I've been struggling with spending too much time on repetitive research tasks in my workflow, like:- Finding specialized professionals (therapists, consultants, etc) - Tracking local tech events and meetups - Checking sports scores and stats - Monitoring job market trendsCurrently building a solution using structured API responses instead of browser automation, but curious how others are...

( Read More... | 2 comments | on HN )