Chat GPT - Open AI, the future of Astronomy

[glend (Glen)]

Over the past few months, since the release of Open AI with CHAT GPT, I have watched countless examples of Python code generating art work, composing music, writing stories, and making the big leap into the provision of answers, outputs, and findings, which are significant jumps over what now seems like rudimentary software of now obsolete applications, including Google Et al.

The question I want to pose to the community here is:

Where is amateur astronomy going, in a new world order where AI is capable of finding anything in the sky, capturing it, rendering it, and displaying it, almost instantly compared to techniques which we might be using today?

[raymo]

Over the next few decades humans will be needed less and less in virtually every field of endeavour that we are currently involved in. This transition has of course been under way for quite some time.
A good illustration of this is the quality of the images now being posted by
newbies in the field of AP. The massive proliferation of software, and to a lesser extent, hardware, is allowing far easier focussing, polar alignment,
processing, etc: etc: This means that if you have the budget and are computer literate, you can eliminate a large percentage of the learning curve. Shortly, processing will be carried out by the software
if the imager so chooses, leaving the human contribution to AP being little
more than the setting up taking down of his/her rig. I find it very sad that the satisfaction gained from the hard work involved in producing an image, and hopefully later on producing improved versions, will be lost.
We of course already have electronic scopes that produce passable images while we wait, and they will only improve.
I think that amateur astronomy, at least as we know it, will cease to exist
in a decade or two.
raymo

[Startrek (Martin)]

Glen ,

Thanks for raising this extremely important topic

In reference to BlurXterminator ( AI based ) ……..

At least the developer of Startools, my post processing software, has maintained his stance on keeping Astrophotography post processing “real” not “fake”

Below is a link I posted a few weeks back , it’s long but worth a read


https://forum.startools.org/viewtopic.php?t=2746

PS: Raymo , you’ve probably seen more changes over the past + 60 years in Astronomy than anyone on this forum and I guess it may sadden you to some extent. But I’m sure this “fake” stuff won’t last the test of time and hopefully in a couple of decades we will still be enjoying the night sky like we do now

Cheers
Martin

[N1 (Mirko)]

Many moons ago, I did some courses in the field of humanities. "What does one do with that?" was a question I often heard, hinting at employment prospects (or lack thereof). My answer was, "it's the last thing to be automated, where humans are rendered obsolete". I would say the same thing today.

I wonder how good AI will ever be at thinking outside the square/ lateral thinking, a process which leads to a lot of scientific discovery and advancement.

Recreational AP will still have its place no matter how good AI based processing becomes, just like visual astronomy.

[dikman (Richard)]

Being able to reach conclusions based on minimal information and using illogical reasoning has always been one of the strongpoints of the human mind.

[AdamJL]

^ I think that’s called “jumping to conclusions” in ordinary lexicon and I agree with you completely.

Me, I’m super excited for an AI future. Loving what the AI based tools are doing with AP. Long may it continue!

[glend (Glen)]

Originally Posted by dikman

Being able to reach conclusions based on minimal information and using illogical reasoning has always been one of the strongpoints of the human mind.

Illogical reasoning is also one if the biggest problems with human minds, based on historical outcomes. And logical to whom? Putin, Hitler, etc.

The AI military systems probably have no regard for certain humanity based rules. Here is a good time to think about Asimov's First Law of Robotics.

I think we can all agree that some sort of ethical framework is required for Open AI, however, the world of Dark AI will continue to evolve.

But can we try to avoid straying from the original question re astro impacts. I know it's hard.

[sharkbite]

Originally Posted by N1

Many moons ago, I did some courses in the field of humanities. "What does one do with that?" was a question I often heard, hinting at employment prospects (or lack thereof). My answer was, "it's the last thing to be automated, where humans are rendered obsolete". I would say the same thing today.

Yup...

back in the 90's i was warned not to take my chosen career path in IT, due to my job being fully automated within the next 5 years.....i'm still waiting....

Yes some parts were automated.....the mundane, boring bits.

This got rid of all the lunk heads, and elevated positions like mine to people who could think.

I see AI as an extension of this - getting the machines to do the stuff we are either not good at, or hate
....so that we can get on with more interesting things...

For mine - i got into Astronomy to see pretty things and photograph them - not spend all night setting up kit.....

Sorry if this sounds a bit blunt - i realise my experience is not the same as others...so mileage may vary!

[glend (Glen)]

Here is a link to OpenAi rules and in it a link to the Open AI community forum.

https://community.openai.com/guidelines

[The_bluester (Paul)]

I think AI in processing astrophotography is likely to be the equivalent for some time of CHAT GPT.

By that I mean they have already shown that CHAT GPT is quite capable of producing an essay to argue a point for instance, that reads well, hangs together grammatically, sounds authoritative but in terms of the subject matter is completely wrong. I was listening to talk on the radio about it and they were talking about in education settings, possibly having to go to oral exams when they have doubts, if a student can go feed a few text prompts at an AI program and get back a well-structured essay that is contextually right (And surely eventually they will) then how do you work out if the student actually understands the subject matter except for giving them a grilling face to face.

The AP equivalent is some of the AI tools which simply features where none exist, they look great, look like details but they come from an unknowable association in "Black box" software. Make sure it has the right training set or the Vela SNR suddenly looks like the "Wall of noses" in Jenolan caves.
The other side of the coin is that for AP it might well eventually be able to take whatever rubbish data you throw at it, identify the object and massage your data until the "Output" looks like the reference image.

Neither option appeals to me in the least. Star removal by AI like StarXterminator is one thing, and I am fairly certain it is inventing detail as it "Removes" the stars (If the star has saturated the pixels in an area for instance, no amount of extrapolation is anything but a guess at what would be there if the star was not) but my use of that type of tool is generally to remove stars from narrowband images before using them as "Lighten" layers to add the NB to LRGB images, the stars in the LRGB are going to push through and obscure the invented data anyway. I also like NoiseXterminator, but that has to have limits too before it is interpolating away detail that is actually there, having mis-identified it as noise.

TL;DR:

I reckon beyond a certain point (Which we are pretty close to IMO) AI tools in AP will not improve the breed. It is not inconceivable to have an AI set up that can identify objects by plate solving and corral whatever rubbish you throw at it into a good image. But is getting out your pencil and drawing a star field on paper for it to solve, then letting it massage your coffee stains into an image of M42 astrophotography?

[glend (Glen)]

Paul, your points assume an already existing body of knowledge on your part, and all of the equipment, software, etc necessary to acquire and process an image. Many others, especially those thinking about getting into astro imaging, or visual observation, will have a learning curve and an investment curve, not to mention the time required.

For a person just developing an interest, Astro AI offers an incredible shortcut in their knowledge building. Face it, just about anything you can image, or observe, is already imaged and stored on the Net somewhere. The tools are already available to view these objects at various focal lengths, in various filter packs, etc in high definition.

For those of us that have gone through the Astro learning and investment curve, i suspect many are as in love with the process as much as the outcome. It is a ritual that we find satisfying. And we spend a lot of time talking here about process.

For New generations, the learning curve will flatten significantly, allowing less obsessive involvement in curating a process, and more time for other things. They will likely not need to buy equipment, worry about the weather, etc, as the AI can give them what they seek.

Sure there is no one Astro AI solution, just a click away today, but people are out there working on it.

[ReidG]

In the world of electronic hardware everything once had to be done with discrete components, and large computers were actually made that way.
Progressively there have been increases in the size and complexity of integrated circuits.
At each stage there have been cries that this will make humans obsolete. What has actually happened is that increasingly complex problems can be solved.
I expect that AI will continue to evolve and improve and become part of our lives. Perhaps Google may have to do a huge and rapid change of direction or perhaps they may simply fade away as many big companies have done in the past.


The fundamental problem facing AI remains that of doing what humans and other animals can do and analyze complex situations they have not been trained to work with and still come to useful conclusions.
ChatGPT if asked for an omelette recipe would probably supply quite a good one but it still has no idea what an omelette is. A school kid would

[julianh72 (Julian)]

I just posed this request to ChatGPT:

Demonstrate "lateral thinking" to develop an innovative means of capturing astrophotography

This was the response:

One approach to demonstrating lateral thinking in astrophotography might involve rethinking the tools and techniques used for capturing images. Instead of relying on traditional telescopes and cameras, for example, one might experiment with new technologies such as:

Drones: Equipping drones with cameras and flying them at high altitudes could provide a unique perspective for capturing astrophotography images.
Balloon-based cameras: Launching cameras attached to balloons into the stratosphere could also offer new angles and perspectives for capturing images of celestial objects.
Augmented reality: Developing an app that combines data from telescopes and cameras with augmented reality technology could create a new way of experiencing and capturing astrophotography images.
Multi-spectral imaging: Using sensors that can capture images across a range of wavelengths, beyond the visible light that traditional cameras pick up, could reveal previously hidden details in astronomical objects.

Nothing truly earth-shattering there - but some food for thought for hackers and makers?

[The_bluester (Paul)]

I think Glen, the biggest problem I have is the conceptual one, what is the point? As you say we are all pretty invested here in equipment, software and knowledge acquisition, to say nothing about aesthetic tastes where everyone is different, and everyone's tastes and preferences evolve over time as well as you learn more.

As a hands on sort of person, I can still see how downloading data to process from Hubble for instance (Or any telescope for hire service around the world) to avoid the expense of the equipment rabbit hole could be very appealing to a lot of people.

Likewise more and more automated "One click" processing software that takes whatever you throw at it and massages it into shape via fair means or foul (Mathematical deconvolution versus AI hallucination techniques as is the current debate)

Where it all falls down for me and (The concept issue) is to use someone else's data and chuck that into inscrutable black box processing software. What is the point? You might as well just go to Astrobin, find an image you like and download that. That is from my "Hands on" perspective. I just can't see how someone who does not aquire the data for themselves and does not do anything much processing wise other than point the black box at the right folder, is going to bother. They might as well use one of the text to image AI's and write "Please make a realistic image of a galaxy as seen from Earth as though through a telescope"

I think the following two posts show the current limitations quite well in terms of AI is currently only as good as the training data. There is no analysis, no actual thinking, just joining the dots between loads and loads of training examples. What does it do if someone comes up with a truly original question or if there is no training data for that, say "Dunno, no one has ever asked that before"?

[dikman (Richard)]

Re- drones and balloons, fine for short exposures but for long(ish) exposures stability and a fixed location would seem to be a necessity. Trying to maintain constant, and long, accurate pinpoint tracking with a drone could be an interesting exercise. Not to mention a balloon, which is dependent on the vagaries of any wind (or atmospheric disturbances).

[The_bluester (Paul)]

Sort of my meaning exactly about the limitations, at any sort of level you would look at those ideas and decide that they were going to be either impracticable (Drones and balloons) or actually so sensible that they are already done (IR photography anyone?) but it is the kind of "Hey, wouldn't it be cool if we could" thought bubbles that would get pulled out of the mass of training data acquired by more or less backing up the internet.

The third (Augmented reality) is sort of cool, but shows that it just associates, not understands. If you understood the question (Demonstrate "lateral thinking" to develop an innovative means of capturing astrophotography) you would not answer with using AR to display it.

[julianh72 (Julian)]

Originally Posted by dikman

Re- drones and balloons, fine for short exposures but for long(ish) exposures stability and a fixed location would seem to be a necessity. Trying to maintain constant, and long, accurate pinpoint tracking with a drone could be an interesting exercise. Not to mention a balloon, which is dependent on the vagaries of any wind (or atmospheric disturbances).

I had exactly the same thoughts when I first read the ChatGPT output - but then it occurred to me: NASA has already solved those issues with the SOFIA instrument (infrared observatory mounted in a Boeing 747 - now retired).

Sure - the average hacker / maker doesn't have access to the sort of resources of NASA, but I don't think it would be insurmountable to give it a try. Put a relatively short focal length / wide angle camera onto a gyroscopically stabilised mount (available on commercial hobby drones, for example), and shoot video with relatively short exposures (< 1 second say), rather than long exposure imagery. I think it would be possible to use stacking software to put together some reasonable images - e.g. night sky / landscape images, but taken from a different viewpoint to the more common ground-based pictures of the Milky Way above the horizon / tree-line.

As a thought-experiment into using AI for "lateral thinking", I thought it might prompt some new ideas for people looking for a new challenge - which it did, for me. Perhaps unsurprisingly - it turns out that it's not a totally original concept - a quick Google search for "drone-based astrophotography" shows people are already doing this:

https://www.youtube.com/watch?v=gvN5lnklDNs
https://fstoppers.com/aerial/drone-v...n-nikon-352660

(Note that in the second link, the subject used a drone to get his camera above the fog bank, so he was able to capture some nice images on a night which would have kept most amateur astrophotographers inside.)

[oska (John)]

This "AI" is not more than fancy pattern matching https://www.youtube.com/watch?v=py5byOOHZM8
ie: these phrases are associated with these other phrases. The filtered phrases are passed on to another pattern matcher that makes reasonable sentences. Done.

From what I gather, without paying too much attention to it or indeed at the risk of being entirely mistaken, BlurX' uses a CNN (or something like it) to match a kernel (PSF) that approximates what the image was possibly blurred/convolved with by the seeing, optics etc and then deconvolves the image with that kernel. If that's true then there's no voodoo, obviously.

[glend (Glen)]

Is Astro AI not already in service, may be not the Open AI variety, but say the software that scans the skies looking at pixel movement to identify small near Earth objects that might represent a collision risk?

[N1 (Mirko)]

Originally Posted by julianh72

I just posed this request to ChatGPT:

Demonstrate "lateral thinking" to develop an innovative means of capturing astrophotography

This was the response:

One approach to demonstrating lateral thinking in astrophotography might involve rethinking the tools and techniques used for capturing images. Instead of relying on traditional telescopes and cameras, for example, one might experiment with new technologies such as:

Well duh