All of the Gaussian Splat embeds that I see on the web require you to create a Gaussian Splat first, and then embed it. I thought, what if we could just turn every photo on the web into 3D.

I built a web component that turns any image URL into an interactive 3D embed. Drag to rotate, pinch to zoom. Install in two lines:

The component fetches from a Cloudflare Worker that either returns a cached Gaussian Splat or generates one on the spot. Splats are ~5 MB, but have a 15 KB preview mesh that you can interact with while it streams in on slower connections.

Works with any image URL.

Docs + live demo: https://mukba.ng/image-3d/docs/ Source: https://github.com/imichaelnorris/image-3d

Comments URL: https://news.ycombinator.com/item?id=48139097

Points: 2

# Comments: 2

I kept trying to optimize my terminal layout and realized I could just run my terminals inside of the browser, and let Claude Code write JavaScript in the same browser tab to customize the experience however I want. It's kind of a terrible idea, but it's my terrible idea, and I love it.

Making the game engine was easy. Making the story consistent, believable, and interesting has been the biggest challenge for me.

I’ve written a few bad novels but never any narrative games, so it’s been a good exercise for me.

Deepsteve is a node server that runs on your machine, so the website is designed to look like DeepSteve's UI. You really just access it at localhost:3000 in your browser, not via deepsteve.com

But now I can see how that would be confusing.

DeepSteve (deepsteve.com) has a similar premise: it spawns Claude Code processes and attaches terminals to them in a browser UI, so you can automate coordination in ways a regular terminal can’t: Spawning new agents from GitHub issues, coordinating tasks via inter-agent chat, modifying its own UI, terminals that fork themselves.

Re: native vs external orchestration, I think the external layer matters precisely because it doesn’t have to replicate traditional company hierarchies. I’m less interested in “AI org chart” setups like gstack (we don’t have to bring antiquated corporate hierarchies with us) and more in hackable, flat coordination where agents talk to each other via MCP and you decide the topology yourself.

Comments URL: https://news.ycombinator.com/item?id=47395031

Points: 2

# Comments: 0

Since last time, I've replaced the video-to-3D pipeline with single-image Gaussian Splatting. A photo now generates in ~10 seconds on a Mac Mini, down from 15-120 seconds for video. You can compare the two approaches—video-based meshes: https://mukba.ng/discover/#videos vs image-based splats: https://mukba.ng/discover/#images

Benchmarks for SHARP between Mac Mini M4 and Macbook Pro M4: https://mukba.ng/blog/2026-01-21-sharp-apple-silicon-benchma...

I've also optimized rendering speed: I've chunked and zstd'd the output so it can start rendering as soon as the first packet comes in.

Why food? I started with Structure from Motion on video, and food was a good constraint because it doesn't move. People look terrible when they blink or shift mid-capture. Now that doesn't matter as much.

Comments URL: https://news.ycombinator.com/item?id=46797821

Points: 2

# Comments: 0

$ exiftool chatgpt_image.png

...

Actions Software Agent Name : GPT-4o

Actions Digital Source Type : http://cv.iptc.org/newscodes/digitalsourcetype/trainedAlgori...

Name : jumbf manifest

Alg : sha256

Hash : (Binary data 32 bytes, use -b option to extract)

Pad : (Binary data 8 bytes, use -b option to extract)

Claim Generator Info Name : ChatGPT

...

Previously the app only produced 3D models and threw away the original video, but incorporating the underlying videos both shows off to new users what type of content they're supposed to record (i.e. a 1 second video of a darkly lit pizza box is NOT going to produce good content), and it makes the output shareable content.

Pose tracking lets me project 3d effects onto the video like the glow in the demo.

Comments URL: https://news.ycombinator.com/item?id=46277991

Points: 2

# Comments: 1

I recently added pose tracking of the 3d model so I can overlay 3d effects onto the underlying video.

Here's a demo: https://mukba.ng/p?id=29265051-b9c7-400b-b15a-139ca5dfaf7e

I'd love to boot this up and see how it runs on a Quest headset

I've been doing this for the last year with YouTube. YouTube is just a search bar now which prevents mindless browsing and distractions.

If I find myself using a site mindlessly I add it to my /etc/hosts file to block them.

So what if a machine can write a novel? I don't even want to read it.

Human intention is what gives meaning and value to my life.

The things that I want to build need me to make them. Why would I wait for a machine to do it later without my imperfect human perspective?

I think it kind of sounds similar to what you were mentioning, but it sounds like the lowest possible latency solution is to stream multiple streams of different bit rates at the same time and then WebRTC picks up the best one it can.

[1] https://bloggeek.me/webrtc-simulcast-and-abr-two-sides-of-th...