| Do you (or plan to) use AI to help you find targets ? | |
|---|---|
| Yes I do ! | |
| No but I will ! | |
| No way, you guys are a bunch of cheaters ;) | |
| Login to vote and view results. |
2.15
#...
·
·
2
likes
|
|---|
I just tried it, for the fun of it, and I was pleasantly surprised with the answer. I didn't expect being that specific would yield any results. Turns out I was wrong  ME "Can you provide a list of nebulae located more than 35 degrees above the horizon and visible in June at the 47th parallel?" CHATGPT To observe nebulae from the 47th parallel north in June, it's essential to consider their height above the horizon and their visibility during this time of year. Here is a list of nebulae visible at more than 35 degrees above the horizon in June from this latitude: 1. Ring Nebula (M57)
2. Dumbbell Nebula (M27)
3. Eagle Nebula (M16)
4. Omega Nebula (M17)
5. Lagoon Nebula (M8)
6. Trifid Nebula (M20)
7. Crescent Nebula (NGC 6888)
8. North America Nebula (NGC 7000)
These nebulae are all visible from the 47th parallel north in June and reach a sufficient height above the horizon for optimal observation. The best visibility will depend on local conditions and the absence of light pollution. |
|
2.15
#...
·
·
2
likes
|
|---|
|
A little more specific. ME "Can you provide a list of nebulae located more than 35 degrees above the horizon and visible in June at the 47th parallel and suitable for focal lengths ranging from 135mm to 400mm" CHATGPTSure, here is a list of nebulae that should be visible from the 47th parallel in June, located more than 35 degrees above the horizon and suitable for focal lengths ranging from 135mm to 400mm:
These nebulae should provide excellent targets for your focal lengths, offering a range of sizes and complexities to capture. Be sure to use a star chart or an astronomy app to confirm their exact positions and best viewing times. |
4.37
#...
·
·
4
likes
|
|---|
|
but why not use the Telescopius filtering section? it gives a ton more specification options (and shows a ton more objects) than ChatGPT I've tested ChatGPT before; sometimes it doesn't get it no matter how much detail is in my question. BTW, It's called "AI", not "IA". |
4.36
#...
·
|
|---|
|
I agree, I don't really see the value when comparing it to the likes of Telescopius or Stellarium for that matter (I prefer the latter one). One of the more enjoyable things for me during off season (may-august) is to scout new projects off the beaten path in Stellarium and/or Telescopius and making notes. I get that this part isn't for everyone, but it adds another dimension to the hobby. I for one am not in a hurry to have lots of objects handed to me by AI, I would find it rather stressfull. The examples also seemed to be pretty basic well known objects. After a while you know which constellations are present or when they will become present. Just like any other map really, it gets familiar. But to each their own! |
|
2.15
#...
·
·
4
likes
|
|---|
|
I had no idea Telescopius could do that. To be honest I am not a big fan of it, I know it is very powerful but I find the interface quite cumbersome. Maybe I should set time aside to take another good look at it. IA = Intelligence Artificielle..................I forgot to translate it, I fixed it  |
|
4.36
#...
·
|
|---|
Eric Gagne: They are extremely useful tools. I agree with you on Telescopius though, I much prefer Stellarium myself - but the one thing Telescopius has which is a huge advantage is the possibility to frame objects but also create mosaics and actually export plans. Those plans can be imported to the Asiair, which I use, and executed from there. Stellarium also offers framing, and if you use NINA you can transfer those framings into NINA, but as far as I know you can't export anything to a file or make mosaic plans there. What I've started doing is using Stellarium like I always have, but planning the projects in Telescopius for exporting it  |
|
2.15
#...
·
|
|---|
Jan Erik Vallestad: You probably already know about it but in case you don't, you can create mosaics plans directly in the Asiair now. I have not tried it myself yet but Windy City Astrophotography on Youtube has a good video about it. https://youtu.be/-_t94WFO_Cs?si=qSzpQAC3NH-JK4sL |
|
4.36
#...
·
|
|---|
|
Yes I've been using it for a couple years now. The only issue with the AA is that it's sky atlas is utterly rubbish - at best. Might as well be star hopping as far as I'm concerned You won't be able to see most of the stuff out there except for the really obvious objects which is a shame. I'd love for them to implement surveys in there. Which in return would make framing and creating mosaics in there viable. |
|
4.37
#...
·
·
1
like
|
|---|
Jan Erik Vallestad: yeah, know what you're talking about some areas of the atlas are actually blurry and you can't really see anything and all the other areas aren't good either; you can't really see the DSOs well |
2.62
#...
·
|
|---|
| Thats why we use stellarium with HIPS... |
2.11
#...
·
|
|---|
| I've been subscribed to AI tools since its first release and use them daily for my work. But I never use it for such purposes because it is not good at calculating and might hallucinate easily. On the other hand, tools like Telescopius give accurate results since it's calculation based. I personally do not recommend anyone to rely on AI's responses on these matters. Although, I might say the title of this post made me curious, I keep pondering if there is a way to integrate them. |
0.90
#...
·
·
1
like
|
|---|
|
In order to find targets, I'm using an iOS app called Observer Pro. What I specifically like about it is that 1) it takes into account my custom horizon (no need to import it in a certain format, the app lets you capture it with your phone camera - and export it to SkySafari and other formats!) 2) it takes into account the DSO magnitude, altittude, location vs the moon, moon phase to calculate its visibility, 3) it calculates the total available imaging time based on the custom horizon, 3) then computes quality imaging time for each DS per night. I also like the fact that it gives you a view of the same info by day and by month (so that you know if this object will become more or less visible in a few days or month). It also has a FoV simulator based on DSS images (hence not great, but OK) After many research online this is the one that fits all my needs.  |
7.61
#...
·
·
2
likes
|
|---|
|
I tried using Chatgpt to write a Pixel Math expression. The first time was successful, well, actually the second time, the first time it gave me a script, not a PM expression. Anyhow, the expression it came up with when I pointed out the mistake worked pretty well, but a small edit improved it. So, later that day, and on a different computer, I tried again to see if, with some feedback, it would come up with the same improvement. This time, and using the exact same initial request, even after several tries chatGPT failed to come up with anything useful…..when I then showed it the response I’d gotten earlier, it said that was a much more ‘eloquent’ solution…..so I asked why I got such a better answer the first time and nothing even workable the second. ChatGPT’s reply was because of the ‘state’ it was in. ‘State’?……like distracted from planning the overthrow of humanity?….. Cheers, Scott |
0.00
#...
·
·
1
like
|
|---|
Gael Gibert: I can fully agree with that. I've been using it for several years and it's one of the best pieces of software for astrophotographers. |
|
2.15
#...
·
|
|---|
|
Interesting answers to my little survey so far.Yes I do ! 4 (20,00 %)No but I will !9 (45,00 %)No way, you guys are a bunch of cheaters ;)7 (35,00 %) I am surprised 35% (so far) sound like they won't even consider it. There is nothing AI did for me here that I could not have done myself with Sky Safari or Stellarium for both of which I have premium licenses. But when I just want a quick list of what is visible for me right now, I wonder why I would spend time and effort to do it manually when AI can give it to me in seconds. One thing AI gives you that apps do not is the ability to filter on anything I want because I just have to write. I spent time on Telescopius last night and I still couldn't figure out a way to do the same. As far as I can tell it cannot:
As I see it,AI is just another tool in my toolbox, it has its purpose and in some circumstances it can be more useful. |
|
2.11
#...
·
·
2
likes
|
|---|
Eric Gagne: This takes seconds if not a minute on Telescopius. I think one just needs to get familiar with the UI once to make it practical. Every parameter you can use is already there. I define my scope and it remembers my scope. Then for that day, I define my parameters: Show me objects 30 degrees above the sky at least X hours, but also these should be brighter than this amount and the size should be between this and this. Doing this is only a few seconds for me. ChatGPT is a LLM, it is not capable of such calculations. The only reason it is giving correct answers at a time is because that specific information was 'luckily' involved in the training set somehow. It might give you a completely wrong answer as well. Because it does not calculate when you ask that question, it predicts depending on the common words in the training set. We tried even training it for simple physics calculations, let alone doing spherical geometry calculations that require a complete dataset of objects. It fails the calculation, this is obvious from the experiments and no surprise because of what it is. And this area lacks the required training set. It will fail you if you rely on that. Use it if you find it practical, but always check if it gives you the correct answer. *See what I refer to as 'luckily': https://x.com/petergyang/status/1793480607198323196 |
|
7.61
#...
·
·
2
likes
|
|---|
|
Yeah…..I gave it a try and it suggested Orion, but Orion is at its least visible point of the year right now….. Cheers, Scott |
0.90
#...
·
·
3
likes
|
|---|
Kay Ogetay: The responses in the original posts aren't even correct. M16, M8 and M20 are all well below 35 degrees from 47 degree North. (M8 and M20 don't go higher than ~20 degrees above the horizon.) |
|
2.15
#...
·
·
2
likes
|
|---|
Xavier Ducrohet:Kay Ogetay: Now that is interesting. I had not yet validated the answer but you are right. I just checked on M8 in Sky Safari and it never gets near 35 degrees in June. |
|
2.11
#...
·
·
1
like
|
|---|
Xavier Ducrohet:Kay Ogetay: No surprise. I'd be very surprised if it was all correct. I didn't make that claim because I did not check. Thanks for looking into that. There is a way to use it though. If you know what you are doing, you can ask for a Python script that makes the calculation. But I have to say, it'll require a lot of testing and debugging. You can make your own Telescopius-like script. And for many, of course, this isn't a more convenient way than just using the Telescopius. |
|
7.61
#...
·
|
|---|
|
Another resource is Gary Imm's Compendium. Old school spreadsheet, but as or more powerful than anything else, I think, and a truly massive endeavor. https://www.garyimm.com/compendium Cheers, Scott |
9.03
#...
·
|
|---|
Scott Badger: Yes, this is what I do. Ai has produce pedestrian results. |
2.41
#...
·
|
|---|
| I thought you meant as part of a program. I think of Target Scheduler in NINA to be an AI engine. |
1.81
#...
·
·
4
likes
|
|---|
| There is quite literally zero benefit to using LLMs and generative AI to select targets for you, it doesn't have any concept of the sky and it cannot recommend anything to you that it hasn't been trained on (Or that it finds on the internet). This feels like another unnecessary "I used AI because I can" type of deal with no real justification or rationale. One Google search of "Beginner targets northern hemisphere" would yield the same results without any potential for hallucinations. |
|
1.81
#...
·
·
1
like
|
|---|
Eddie Pons: it is a purely algorithmically driven system... what about it is "AI" at all? You literally define the conditions for it to operate under. |
