this might finally be smart enough and fast enough for jarvis. hard to feel like iron man when your assistant takes 8 seconds to decide to pause your music
I completely understand this. I’ve worked on robot hands and 5.6/Fable 5 were practically useless at helping me debug anything visually.
What I have found super useful actually is having models make a interactive 3d viewer in which I use move / highlight / paint (soft body painting directly onto the geometry for issues and different colors mean different failures). This gives a much better way to communicate the physical relationships and positions that are hard to get across in a labeled screenshot.
Its for sure still a lot of manual work so the "seeing-eye dog" description definitely holds. But I have found that after a couple of examples with the extra context the model gets much better at handling the problem and becomes useful.
Ive been played. Me and my brother used to play this all the time. He would always beat me and whenever I would win it would be a momentous occasion. Turns out his build was directly on the pareto frontier and mine was not even close. Damn you brother. Hes totally screwed next time we play
Have you ever walked or run to the beat of a song, or tapped along without even thinking about it?
This morning I was driving on the highway listening to Paranoid by Black Sabbath, cruising around 75 mph, and I noticed the beat of the song lined up perfectly with the lane markings passing by my car.
I started wondering if I could do that intentionally, so I skipped through a bunch of songs trying to match the beat to the lines (I learned pretty quickly that I couldn’t).
Then I wondered if this would work on any highway, and sure enough, there’s actually a standard for the length and spacing of lane markings in the US.
Anyway, I wanted to cheat, so I built this.
You type in a song, and it tells you what speed to drive so the beat lines up with the lane markings.
It uses the Deezer API to get a song’s BPM. If there’s no BPM available, it takes a sample from the audio preview and tries to estimate the BPM using PercivalBpmEstimator. I tried my best to minimize errors, but every once in a while the BPM of a song is still a little off.
The inception effect here is hilarious. Watching this get its own front page while the subtitle lags behind with the previous top posts is weirdly funny.
I made something related to this with whisper. It would just constantly listen and periodically do a search to find a picture/video/gif from the web, relevant to what you're talking about, and show it.
HN comments really can't beat the spectrum stereotypes...
But seriously, the parent comment isn't saying the technical fact a browser can see your cursor's coordinate is unnerving. They're saying the experience of being reminded of this fact is unnerving.
Technically, every time you take a bus ride the driver can just decide to crash the vehicle and kill the passengers and himself. This fact itself isn't unnerving -- it's just how buses work. But if there were a poster on the bus reminding passengers of that, that'd be quite unnerving.
I spent a few hours trying to get this to work, and I couldn’t get it to produce usable results on anything except the training data, even with very simple drawings.
I noticed in the GitHub that they mention it is only around 60% reliable even on their own training data, but the image shown on the front page feels pretty misleading. I made 10 images that were very similar in complexity to the examples shown, and even after running it around 50 times on each image, not a single one worked correctly. In the rare cases where it produced something, the output was completely wrong.
This seems pretty misleading in its current state and definitely needs more work.
When skimming a research paper in addition to abstract don't forget to read "limitations and future work" and "conclusions".
In the limitation section they are quite direct with it: "images used .. are mostly isometric and noise-free CAD-images" and "limited CAD vocabulary used in this study needs to be extended by including more sophisticated CAD tokens such as revolve operation, edge operation (e.g., fillets/chamfers)". It currently supports only series of pads (can be subtractive). Many simple beginner exercises of seemingly similar complexity don't fit those constraints. Some of the parts shown could be more naturally created using wider set of tools, but technically can be created using only pads.
So even if you tried with clean screenshot of simple 3d model, it will likely fail if camera settings aren't right, and it will fail if model can't be represented using series of pad operations. Anything containing spheres, cones, nearly all lathe parts, fillets which can't be included in 2d sketches will fail. In theory arbitrary extrusion angles are supported, but all examples showed only axis aligned parts.
That said I wouldn't be surprised if it failed even if you considered exact limitations not just similar complexity in your attempts.
Assuming images in the googledrive are the training data, "mostly isometric and noise-free CAD images" is a bit of understatement. All of them are at very specific angles using and single style. Specific solid gray infill color for "images", and white infill with weird shading around perimeter for "sketches". Both with white background and pixelated non antialised 1px lines. No reason to expect it capable of processing anything which doesn't have exactly same visual style. For practical product that would have to be solved but that wasn't really the point of this research. All the style transference papers have show that it's more or less solvable problem, but for a paper exploring what model architecture and 3d representation could work best for AI cad it seems like unnecessary distraction that would only bloat the training costs and time. Most annoying part is that it makes hard to test the model with your own inputs.
I’m also confused by their examples. All of them seem to be perfect renders/exports from 3D models — this is not the use case where I see it the most useful. Making a parametrized CAD model out of a hand-drawn sketch — yes, please
