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.
I asked it about designing a 12 V solar system for a garden shed and it got everything but the broadest of strokes wrong. It figured out there should be a solar panel, a solar charge controller, a battery and some loads, but the wiring was non-sensical and when I drilled in on the solar charge controller settings etc. it completely fell apart. Absolute non-starter for any information you plan on depending on, but good entertainment value and impressive execution.
I have a Mac Pro 5,1 taken apart on my desk right in front of me. I asked it for a diagram of the 5,1 internals. While it was MacProish looking, it was wrong about every visual element. The text fields were right at first glace. Every click I did was basically all wrong too.
Visually it looked cool, but actually the first time Ive seen AI be wrong constantly since maybe 2023.
Went to the website, typed in "Jeep Wrangler JK engine bay with components labeled" (Since I'm intimately familiar with JK engine bays). Seems like a pretty analogous test to what you did, if anything an even easier test.
Let's see what we get .. a very nice looking diagram of a wrangler engine bay with components labeled, looks good.
But wait ..
- The brake fluid reservoir is on the wrong side of the engine bay
- Where the brake fluid reservoir is, it's labeled as the coolant overflow tank, and while the actual coolant overflow tank does exist in the diagram, it has no label.
- The battery is on the wrong side of the engine bay.
- The top of the front grill is labeled as the "oil filter cap".
- The oil fill cap is in the wrong place.
- Half of the battery is labeled as the fuse box, when the fuse box is correctly shown, but unlabeled, on the other side of the engine bay.
- It shows two different windshield washer reservoirs next to each other.
I could keep going on ...
Now I tried clicking on the incorrectly labeled coolant overflow reservoir and it switches to a new page which now shows a completely different looking coolant overflow, but now it's at least located in the correct place in the engine bay.
But of course it doesn't look remotely like the actual coolant overflow container. It also shows the radiator cap as on the top of the coolant reservoir, when in reality it is very much on the top of the radiator itself.
Like .. I can find fault with every aspect of it. But of course, if you didn't actually know much about the topic it'd all look fairly believable. The story of LLMs basically.
I also replied because I asked it about a Mac Pro case I had right in front of me. Mostly right words, totally wrong visuals.
And while I see what you mean by 'story of LLMs', I ask LLMs about things I know often, and for the last 12 months theyve been pretty dang accurate. This ai visual example is the strongest 'its just guessing' Ive seen in years. For a demo, pretty cool still though. Not sure why OP exaggerated, or simply doesnt know his car as well as he thinks he does.
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" } ] } ] } }
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'm sure that the absolute avalanche of VC money that is about to be thrown at them will compensate for this modest outlay. The creators obviously know they're onto a sure thing here.
I didn't want to even try it because of similar. ("immigrant mentality" they call it around here. it's not a pejorative. TLDR: frugal because starting life over)
and it's really slow. I didn't end up waiting. Not a slight to the creators, let them create. It's just really freaking slow I didn't wait.
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.
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 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.
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.
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.
It's perfect for toddlers (I mean that in a good way), it's the infinite answer to the infinite "What's that?" series of questions they can generate. Make everything a hyperlink and it's almost like a LLM mind map of knowledge.
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.
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.
Went to the website, typed in "Jeep Wrangler JK engine bay with components labeled" (Since I'm intimately familiar with JK engine bays). Seems like a pretty analogous test to what you did, if anything an even easier test.
Let's see what we get .. a very nice looking diagram of a wrangler engine bay with components labeled, looks good.
But wait ..
- The brake fluid reservoir is on the wrong side of the engine bay
- Where the brake fluid reservoir is, it's labeled as the coolant overflow tank, and while the actual coolant overflow tank does exist in the diagram, it has no label.
- The battery is on the wrong side of the engine bay.
- The top of the front grill is labeled as the "oil filter cap".
- The oil fill cap is in the wrong place.
- Half of the battery is labeled as the fuse box, when the fuse box is correctly shown, but unlabeled, on the other side of the engine bay.
- It shows two different windshield washer reservoirs next to each other.
I could keep going on ...
Now I tried clicking on the incorrectly labeled coolant overflow reservoir and it switches to a new page which now shows a completely different looking coolant overflow, but now it's at least located in the correct place in the engine bay.
But of course it doesn't look remotely like the actual coolant overflow container. It also shows the radiator cap as on the top of the coolant reservoir, when in reality it is very much on the top of the radiator itself.
Like .. I can find fault with every aspect of it. But of course, if you didn't actually know much about the topic it'd all look fairly believable. The story of LLMs basically.
But still coming from a frugal background I still cannot wrap my head around this
and it's really slow. I didn't end up waiting. Not a slight to the creators, let them create. It's just really freaking slow I didn't wait.
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.
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.
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.
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.