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.
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
I mean, do you have any hobbies or does every cent you have go to food, rent, and savings, with no frivolities, not even a drink after work or food that isn't rice and beans? Some people play video games or painting or carpentry or what have you. Instead of spending money on alcohol or sports, some people with FAANG-level salaries choose to spend their entertainment budget on GenAI art projects. Not your cup of tea, totally fine, but I suspect your budget has something others could choose to find frivolous if someone wanted to nitpick.
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" } ] } ] } }
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.
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.
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.
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.
Interesting! To join the cavalcade of others sharing their experiences:
I first asked it "how big are geckos". It gave me a cool comparison diagram between three gecko extremes (leachianus, Jaragua dwarf gecko, and leopard gecko, if curious). Info all looked correct. Drilling into the Jaragua brought me to a less-impressive page with utter gibberish text and duplicated info boxes. So it goes. I drilled further, but they were more esoteric topics I'm less versed on (lamellar setae), I can't evaluate the accuracy without further research.
I also gave it something broader: "tokay gecko". More duplicate info boxes, and for some reason it "drew" two geckos on top of each other. Kind of cute, but tokays are extremely territorial, so happy cohabitation isn't their default (though it's not unheard of).
Still, despite the issues, I thought it was very neat.
Since ecco the dolphin just had two remasters and a new game announced, I decided to ask for it to show me a map of the first stage of tides of time. Should be easy, it just has to search for it and then generate something off of it. The stage is mostly empty too, just an open area, then a large opening with an upward current that leads to a separate bay with a warp ring. Three spaces, some dolphins and a circle.
It did a diagram that has absolutely nothing to do with the actual stage, not even close. And tells me a complete whole slew of completely wrong information. It shows pod of dolphins that teach you to dash attack (you know it by default). It shows a power sonar crystal (the sonar is a default ability, there is a "power" sonar I guess, but it is not obtained from crystals, and while the game features crystals, there are none in the game until level 3 and they look nothing like the diagram's). It shows air pockets... which are just bubbles (In the game, there are actually air refilling bubbles, but air pockets would refer to a small bit of open air in an underwater tunnel, like, the actual, you know, real life geological feature.)There are some medusas far off in the background in the image (They're yellow. The ones in the game are clear. They are also not present until later levels). An exit cave leads to the sea of silence (An actual stage. Wrong game.). A random cave says "Health source" (???? You do heal by eating fish but???). There is no warp ring.
So basically, the ONLY correct elements in the diagram are the presence of dolphins and the fact the diagram is labeled "Home Bay". Every single other element on this is wrong and would be wrong for all iterations of the Home Bay.
I have an old door on the back yard, been planning to make a bike shelter this week so I asked it to make me a plan. It drew a regular shed with an "upcycled door". But no sign of where a bike should fit into it. No bike would ever fit in that thing, and the only structure it showed how to construct didn't resemble the actual finished thing.
Like every other AI demo I've tried ever, impressive on the surface, but the system fundamentally doesn't understand what it is doing
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.
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.
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 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?
Interesting, for me your "permalink" shows SSD labeled as DDR4/DDR5, cooler named as CPU, "Praer Caplu", no M.2, etc. I guess it regenerates images ever so often, so can't predict what will be shown next time.
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
82 comments
[ 2.1 ms ] story [ 114 ms ] threadFor 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.
But still coming from a frugal background I still cannot wrap my head around this
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.
This very well could be a sneak-peek into how educational resources might look like in the future.
In the age of such enormous computing power, this sort of thing is pure waste.
MS Encarta CDs were faster and more in-depth.
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.
I first asked it "how big are geckos". It gave me a cool comparison diagram between three gecko extremes (leachianus, Jaragua dwarf gecko, and leopard gecko, if curious). Info all looked correct. Drilling into the Jaragua brought me to a less-impressive page with utter gibberish text and duplicated info boxes. So it goes. I drilled further, but they were more esoteric topics I'm less versed on (lamellar setae), I can't evaluate the accuracy without further research.
I also gave it something broader: "tokay gecko". More duplicate info boxes, and for some reason it "drew" two geckos on top of each other. Kind of cute, but tokays are extremely territorial, so happy cohabitation isn't their default (though it's not unheard of).
Still, despite the issues, I thought it was very neat.
It did a diagram that has absolutely nothing to do with the actual stage, not even close. And tells me a complete whole slew of completely wrong information. It shows pod of dolphins that teach you to dash attack (you know it by default). It shows a power sonar crystal (the sonar is a default ability, there is a "power" sonar I guess, but it is not obtained from crystals, and while the game features crystals, there are none in the game until level 3 and they look nothing like the diagram's). It shows air pockets... which are just bubbles (In the game, there are actually air refilling bubbles, but air pockets would refer to a small bit of open air in an underwater tunnel, like, the actual, you know, real life geological feature.)There are some medusas far off in the background in the image (They're yellow. The ones in the game are clear. They are also not present until later levels). An exit cave leads to the sea of silence (An actual stage. Wrong game.). A random cave says "Health source" (???? You do heal by eating fish but???). There is no warp ring.
So basically, the ONLY correct elements in the diagram are the presence of dolphins and the fact the diagram is labeled "Home Bay". Every single other element on this is wrong and would be wrong for all iterations of the Home Bay.
For a visual search tool, this sucks at visuals.
Like every other AI demo I've tried ever, impressive on the surface, but the system fundamentally doesn't understand what it is doing
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.
[1] https://news.ycombinator.com/item?id=34503418
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.