georgesmith9914

georgesmith9914 on Hacker News

I built a rejection therapy practice tracker

Posted by georgesmith9914 on Tuesday April 07, 2026 @03:38PM
from the bubbling.dev dept.

https://bubbling.dev/practice/rejection-therapy

( Read More... | no comments | on HN )

Describe a dashboard, get a working app in 3 minutes

Posted by georgesmith9914 on Wednesday April 01, 2026 @02:58PM
from the bubbling.dev dept.

https://bubbling.dev

( Read More... | no comments | on HN )

Re:Describe an app in one sentence, get it built and shipped within mi... on Monday March 23, 2026 @09:52AM (#47489562)

Thanks a lot. Also, great to have your feedback in case you can try creating an app and share how it went.

Describe an app in one sentence, get it built and shipped within minutes

Posted by georgesmith9914 on Sunday March 22, 2026 @05:15PM
from the bubbling.dev dept.

https://bubbling.dev/

( Read More... | 4 comments | 2 points | on HN )

Re:Describe an app in one sentence, get it built and shipped within mi... on Sunday March 22, 2026 @05:15PM (#47482228)

I built bubbling.dev — type a plain-English description for an app and it generates a real app, then deploys it to a live URL.

Demo video: https://1drv.ms/v/c/bef4ed7c37dc4a70/IQBBRjjQ9LvWSot9REBVwNa...

No templates — it writes real code each time. You can refine by chatting with it.

Free beta.

Re: on Monday February 23, 2026 @06:33PM (#47130618)

NanoAgents lets you build and run small AI agents entirely in-browser using WebGPU — no API keys, no server calls, zero cost per query.

Stack: Next.js + WebLLM (Qwen2.5 0.5B–3B quantized models). Features include a skill chain system, real-time streaming output, short/long response modes, and a fork-and-customize workflow.

Everything runs on your GPU. The models are ~300MB–1.5GB and cached after first download. Works best in Chrome with WebGPU support.