Interesting idea, but just about everything is failing for me. Probably the HN hug of death happening.

  Gemini generateContent request failed: { "error": { "code": 429, "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. ", "status": "RESOURCE_EXHAUSTED", "details": [ { "@type": "type.googleapis.com/google.rpc.Help", "links": [ { "description": "Learn more about Gemini API quotas", "url": "https://ai.google.dev/gemini-api/docs/rate-limits" } ] } ] } }

This seems like an expensive product to subject to the HN hug of death.

The sample videos on the tweet are very very cool.

Unfortunately it didn’t really work for me, I’ll try it out in a few days when the traffic’s died down.

Interesting idea and cool demo.

For this to really be practical you'd need a way to run networks many times faster and more efficiently than today's GPUs. This is too slow to work even with cloud GPUs powering it.

Maybe someday.

Very cool project ! I fear this might have a pretty high hallucination potential (with current models) the deeper you dig into the base image/context and clicking on potentially unrelated elements in the image. Nevertheless, love the idea.

Couldn't get it to load (probably getting hammered right now) but the concept is interesting. Feels like one of those things where the tech needs to get 10x cheaper before it actually makes sense as a product.

It looks pretty nice - reminds me of Dorling Kindersley books. But the graphics, whilst stylised, are pretty hit-and-miss. Great idea, just a bit too soon.

So cool! Love the exploration into new interfaces.

This would make an amazing educational tool

This is very cool, if a bit glitchy right now (probably thanks to HN popularity). I used to this to generate infographics of the rear subframe, diff carrier, and rear suspension of my car and to get detailed specifications on the bushings, suspension members, and other components. Most of the information matches what I already know, and could be really useful if trained specifically on manufacturer/dealer shop manuals to create interactive models of vehicles you can drill to and get part numbers and specifications for any component on a car.

I just asked it to create a torque spec diagram of the suspension for my car, a subject I'm pretty familiar with. It amazingly drew everything correctly, displayed the correct torque figures and allowed me to click on individual components to zoom in further, providing more specs.

Genuinely one of the most impressive demos I've tried in a long time. I was able to use it almost like a living version of a classic illustrated Haynes workshop manual.

Cool project, but just a side thought I was having about how do people have resources and the money to make things like this and make it avl for public, I mean it's fair to say they have their own GPUs or if they are using api keys for gpt or Gemini with enterprise subsidized inference

But still coming from a frugal background I still cannot wrap my head around this

This is one of the more unique ideas i've encountered in a long time

Game changer when the technology catches up

This is real nice, wow. Congratulations.

This very well could be a sneak-peek into how educational resources might look like in the future.

The worst part of this sort of slop is the attention it squanders by being glacially slow.

In the age of such enormous computing power, this sort of thing is pure waste.

MS Encarta CDs were faster and more in-depth.

Fun. But just as flawed as any LLM.

https://flipbook.page/n/6bd29678afc04b799276f4d3d62cc18e

I like the visual style it produces, great for educational material. What is it called?

Very cool as a demo. I tried something information-dense, a poker pre-flop chart for a specific stack depth (40BB BTN vs UTG rfi) and it was about what I expected. It doesn't even resemble a poker chart and there's no salvageable information as far as I can tell. Not really something this should be able to do though.

https://flipbook.page/n/d48526ab345c4880a3b2171785508f52

Beyond the training boundary. Seems a propos for "an infinite visual browser". I'm just not clear on how we get to the beyond part of it.

https://flipbook.page/n/f8982ddfd3ef4cbcb2ad8449d7d049b6

It's pretty cool. I created a beautiful isometric illustration of home garden, which is worthy of being featured in a real book or magazine. I really like the isometric view to explain things, and the color palette is consistent and pleasant.

This is so good and so fun! :D

Congrats on the launch! This is an amazing product. Something I would add is a panel with sources in case someone wants to have a deep dive in the information. My 2 cents: This could be transformed to a state of the art teacher kind of product

I typed in the address of my childhood home, and breathed a sigh of relief when it showed a random home with solar panels and 'clean modern sustainable living' which my childhood home was not. Even added solar panels.

General design was correct, and it included the name of a town just nearby.

Not a surprising result, but made me reflect on what a weird world we now live in.

Ah I was thinking this created the webpage itself, which I always thought was an interesting concept. Some future where the application is crafted in realtime to fulfill the needs of the user. Has anyone made something like this?

Fun. Uploaded a Kookaburra and got an Encarta like experience zooming on different things.

The images I upload are displayed with an incorrect aspect ratio.

Neat project though!

This wins the internet.

I went from Cat Photos into History of Victorian Cat Photos With Props like Miniature Tea Sets And Velvet Chairs And Humorous Captions On Calling Cards In Visually Ironic Aristocratic Cooperplate Font The Victorian Meme Script With High Stakes Expectations Anchored In A World With Human Dignity As It Relates To Modern Memes in just a few clicks.

Oddly specific, but that was exactly what I needed to see today.

This is fun. I started with "all hail the glow cloud" and now I'm clicking to wander around Nightvale. It's not exactly suprrising that it knows all of the lore, but it paints a pretty cohesive picture...

Incredible AI visualization tool

Very cool idea. Wish it could render faster.

So cool! People being critical of it not being accurate, but from a technology concept it’s super awesome.

I kind of find this absolutely infuriating for reality, but super fun for diagrams of things like 'interdimensional subcutaneous engineering' or whatever scifi/fantasy word salad you want to throw at it

This is just epic. Really amazing.

This kind of thing would be great if we could have large local models sometime in the future.

Sneed's Feed and Seed (Formerly Chuck's)

https://flipbook.page/n/4a5e1797903b478c876a35e64c6c57fe

Didn't quite nail the labeling of each piece correctly for a small form factor PC build:

https://flipbook.page/n/12267bbfdeb043c3aa477337950b2b71

- M2 is labeled as GPU

- GPU is labeled as M.2 and RAM?

- RAM is labeled as GPU

- Random plant inside the case?

- This is also not a typical layout for a SFF PC

Great demo, interesting transitions and UI, but the model / generated information is definitely not correct.

It's like "GPT is all you need for the backend" [1] on steroids

[1] https://news.ycombinator.com/item?id=34503418

This is not really working for me at all, the second images always look near identical to the first with some minor changes. Maybe my prompts are the issue? Anyone have some good prompts?