Giving this a quick spin and I like what I'm seeing. I gave it a picture of Paolo Veronese's Lament over the Dead Christ [0] and asked what was going on in the background.
> The painting depicts the scene of the crucifixion of Jesus Christ. In the foreground, there is a group of people standing around the cross, including Mary, the mother of Jesus, and the two thieves who were crucified with him. In the background, there is a hill with a group of people standing on it, watching the crucifixion. The sky is dark and stormy, with lightning illuminating the scene. The overall mood of the painting is one of sadness and tragedy.
Then I asked for a sonnet on it:
"In this painting, we see the scene of the cross
Where Jesus is crucified, with Mary at his side
And the thieves who were crucified with him
In the background, a hill with people standing
Watching the tragic event unfold
The sky is dark and stormy, with lightning flashing
Illuminating the scene of the crucifixion
The mood is one of sadness and tragedy
As we contemplate the sacrifice of Jesus
But even in death, he shows us the way
To love and forgiveness, to live another day
And so we remember the crucifixion
And the love that Jesus showed us that day."
So...not quite what I was expecting, but it's progress!
Could you describe the image as thoroughly as possible? Please include the content, any noteworthy symbology, techniques or styles, what kind of media, guess at the artist or identify any attribution, then attempt to describe the theme or idea it represents?
Got this
The image is a painting of a child running down a dirt road with a kite in hand. The child is wearing a yellow shirt and blue shorts. The background is a mix of urban and rural elements, with buildings and trees in the background and a field of grass in the foreground. The style of the painting is a mix of realism and abstraction, with a focus on the child and the kite. The artist may be attempting to convey a sense of freedom and playfulness, with the child running with the kite representing the joy and wonder of childhood.
The medium used is oil paint on canvas. The artist may have used brushes and other tools to create the different textures and effects in the painting. The artist may have also used underpainting to establish the composition and values before adding the final layers of color and detail.
It is difficult to identify the artist without more information, but the style and technique of the painting suggest that it may be the work of an artist who is skilled in realism and abstraction, and who is interested in exploring themes of childhood and playfulness.
> This painting appears to be a depiction of a child running down a dirt road with a kite in hand. The child is wearing a yellow shirt and blue shorts, and the background is filled with various colors and shapes. The overall mood of the painting is playful and carefree.
What's amazing is that it has correctly described the scene including details such as:
- A boy
- On a dirt road.
- Having a Kite in hand.
- Wearing Yellow shirt and blue shorts.
I never know what to expect anymore. We live in a world where computers can describe paintings and write sonnets about them but a half-trillion dollar car company can't figure out how to parallel park with eight cameras.
DriveGPT as it hits 2 parked cars and runs over a dog: "Apologies for the confusion earlier. You are correct that the cars were in the planned local planner path..."
Yeah, and I'm still completely lost as to why resolution is such a limiting factor. If you know you're drawing a soccer ball why is a 512x512 soccer ball so much easier than a 1024x1024 soccer ball?
There are a few cases where people have used ChatGPT to generate SVG[0], with mostly unimpressive results. I'm sure sooner or later models will be developed specifically for creating vector drawings instead of raster, including with the ability to apply textures and gradients.
Also, the resolution of Stable Diffusion's output isn't much of a limitation if you're willing to use other tools to massage the output into something professional-quality. See [1]
It's not lidar they need. BMW, Mercedes, Porsche, etc. All can park themselves almost perfectly every time. Teslas can't, and will take 5x as long to do it when they can, if the computer can even bother to recognise the space.
It's software. Original Teslas with AP1 better than Teslas own in house software on their latest AP.
Remember that "cameras" aren't as good as human perception because human eyes interact with the environment instead of being passive sensors. (That is, if you can't see something you can move your head.)
Plus we have ears, are under a roof so can't get rained on, are self cleaning, temperature regulating, have much better dynamic range, wear driving glasses…
Which sounds like a lot until you realize 1) we drive over three trillion miles a year in the US, and 2) the majority of those accidents are concentrated to a fraction of all drivers. The median human driver is quite good, and the state of the art AI isn't even in the same galaxy yet.
I keep hearing this argument over and over, but I find it uncompelling. As a relatively young person with good vision, who has never been in an accident after many years of driving, and who doesn't make the kind of simple mistakes I've seen the absurd mistakes self-driving cars make and I would not trust my life to a self-driving car.
Asking people to accept a driverless car based on over-arching statistics is papering over some very glaring issues. For example, are most accidents in cars being caused by "average" drivers or are they young / old / intoxicated / distracted / bad vision? Are the statistics randomly distributed (e.g. any driver is just as likely as the next to get in accidents)? Because the driverless cars seem to have accidents at random in unpredictable ways, but human drivers can be excellent (no accidents, no tickets ever), or terrible (drive fast, tickets, high insurance, accidents, etc). The distribution of accidents among humans is not close to uniform, and is usually explainable. I wouldn't trust a poor human driver on a regular basis, nor would I trust an AI because I'm actually a much better driver than both (no tickets, no accidents, can handle complex situations the AI can't). Are the comparisons of human accidents being treated as homogenous (e.g. the chance of ramming full speed into a parked car the same as a fender-bender?). I see 5.8M car crashes anually, but deaths remain fairly low (~40k, .68%), vs 400 driverless accidents with ~20 deaths (5%), I'm not sure we're talking about the same type of accidents.
tl;dr papering over the complexity of driving and how good a portion of drivers might be by mixing non-homogenous groups of drivers and taking global statistics of all accidents and drivers to justify unreliable and relatively dangerous technology would be a strict downgrade for most good drivers (who are most of the population).
It's all trade offs. I'm just spitballing here, but if you have limited resources, you can either spend cash/time on lidar or invest in higher-quality mass-produced optics, or better computer vision software. If you get to a functional camera-only system sooner, might everyone be better off as you can deploy it more rapidly.
Manufacturing capacity of lidar components might be limited.
Another might be reliability/failure modes. If the system relies on lidar, that's another component that can break (or brownout and produce unreliable inputs).
So in a vaccum, yea a lidar+camera system is probably better, but who knows with real life trade offs.
(again, I just made these up, I do not work on this stuff, but these are a few scenarios I can imagine)
While ultrasonic sensors would be fine for parking, they don't have very good range so they aren't much help in avoiding, for example, crashing into stationary fire trucks or concrete lane dividers at freeway speeds.
From my experimentation, LLMs tend to kind of suck at rhyme and meter, and all but the simplest types of poetry, so even if you'd specified it probably wouldn't have been able to deliver.
This is definitely something they could be trained to be much better at, but I guess it's hasn't been a priority.
> The painting depicts the scene of the crucifixion of Jesus Christ. In the foreground, there is a group of people standing around the cross, including Mary, the mother of Jesus, and the two thieves who were crucified with him. In the background, there is a hill with a group of people standing on it, watching the crucifixion. The sky is dark and stormy, with lightning illuminating the scene. The overall mood of the painting is one of sadness and tragedy.
Then I asked for a sonnet on it:
"In this painting, we see the scene of the cross
Where Jesus is crucified, with Mary at his side
And the thieves who were crucified with him
In the background, a hill with people standing
Watching the tragic event unfold
The sky is dark and stormy, with lightning flashing
Illuminating the scene of the crucifixion
The mood is one of sadness and tragedy
As we contemplate the sacrifice of Jesus
But even in death, he shows us the way
To love and forgiveness, to live another day
And so we remember the crucifixion
And the love that Jesus showed us that day."
So...not quite what I was expecting, but it's progress!
[0] https://en.wikipedia.org/wiki/Lament_over_the_Dead_Christ_(V...