How Can AI Be Used for Space Applications?

[Robotbeat]

Here’s an article on AI being used for planetary exploration and astronomy:
https://www.space.com/solar-system-planetary-science-machine-learning

And here’s the summary of the article that I had ChatGPT generate:

Machine learning is changing how scientists study space by allowing computers to identify patterns in data and make decisions, predictions or classifications. This can save time for scientists by identifying phenomena such as boulders on other planets, explosive volcanoes on Mercury and vortexes in Jupiter's atmosphere, among other things. In the future, artificial intelligence could be used in space probes to enable them to make real-time responses to hazards and land autonomously, rather than relying on communication with Earth that can take several hours. Machine learning and artificial intelligence could also be used to help plan future missions to bodies such as Jupiter's moon Europa.

[sanman]

Here’s an article on AI being used for planetary exploration and astronomy:
https://www.space.com/solar-system-planetary-science-machine-learning

And here’s the summary of the article that I had ChatGPT generate:

Machine learning is changing how scientists study space by allowing computers to identify patterns in data and make decisions, predictions or classifications. This can save time for scientists by identifying phenomena such as boulders on other planets, explosive volcanoes on Mercury and vortexes in Jupiter's atmosphere, among other things. In the future, artificial intelligence could be used in space probes to enable them to make real-time responses to hazards and land autonomously, rather than relying on communication with Earth that can take several hours. Machine learning and artificial intelligence could also be used to help plan future missions to bodies such as Jupiter's moon Europa.

So I'm curious - did you simply feed it that URL as part of your input, and have it generate its summary on that basis?
If so, that's a pretty nifty trick - gonna have to use that more often.
It would be intriguing if we users can influence ChatGPT by feeding it reading material of our own choosing.

[DanClemmensen]

Here’s an article on AI being used for planetary exploration and astronomy:
https://www.space.com/solar-system-planetary-science-machine-learning

And here’s the summary of the article that I had ChatGPT generate:

Machine learning is changing how scientists study space by allowing computers to identify patterns in data and make decisions, predictions or classifications. This can save time for scientists by identifying phenomena such as boulders on other planets, explosive volcanoes on Mercury and vortexes in Jupiter's atmosphere, among other things. In the future, artificial intelligence could be used in space probes to enable them to make real-time responses to hazards and land autonomously, rather than relying on communication with Earth that can take several hours. Machine learning and artificial intelligence could also be used to help plan future missions to bodies such as Jupiter's moon Europa.

So I'm curious - did you simply feed it that URL as part of your input, and have it generate its summary on that basis?
If so, that's a pretty nifty trick - gonna have to use that more often.
It would be intriguing if we users can influence ChatGPT by feeding it reading material of our own choosing.

As I understand it, the training dataset for ChatGPT is not being augmented. It was frozen in 2021. This is one reason ChatGPT knows very little about itself. I got this potentially incorrect information from a single sentence in a non-technical article on ChatGPT, so it might be wrong. I'm  not sure how one of these systems will evolve it is allowed to incorporate non-curated information indiscriminately. I suspect this is one the areas Google is researching intensively in reaction to ChatGPT.
   https://mezha.media/en/2022/12/22/google-is-panicking-over-the-ability-of-the-chatgpt-bot-to-answer-user-questions/

[JohnFornaro]

https://forum.nasaspaceflight.com/index.php?topic=57207.msg2442453#msg2442453

********

More from ChatGPT from OpenAI.

Like other GPT language models, ChatGPT clearly makes for a good politician: provides a few paragraphs of waffle without meaningfully answering the question.

Of course.

There's an outcry any time an AI doesn't emit a "politically correct" answer. It's no wonder engineers train their AI to talk like a politician.

No, it's a byproduct of AI being trained to assemble coherent sentences ... from a vast training set rather than forming a separate knowledge graph and constructing sentences based on that graph. The chatbot has no understanding of the data it is dispensing, only an understanding of how closely related the prompt is to sentences it has already observed. Political correctness is of minimal concern beyond trying to avoid poisoned data in the training datasets ...

As I understand it, the training dataset for ChatGPT is not being augmented. It was frozen in 2021. This is one reason ChatGPT knows very little about itself. I got this potentially incorrect information from a single sentence in a non-technical article on ChatGPT, so it might be wrong. I'm  not sure how one of these systems will evolve it is allowed to incorporate non-curated information indiscriminately. I suspect this is one the areas Google is researching intensively in reaction to ChatGPT.
   https://mezha.media/en/2022/12/22/google-is-panicking-over-the-ability-of-the-chatgpt-bot-to-answer-user-questions/

Reading the above passages suggests that ChatGPT is indeed being fed curated material by its trainers.  It's not a surprise then, that google might be concerned with the very real dangers of unsafe input being asked of ChatGPT.

This opinion of mine is confirmed in the article:

https://mezha.media/en/2022/12/22/google-is-panicking-over-the-ability-of-the-chatgpt-bot-to-answer-user-questions/

Google is reluctant to share its technology because, like ChatGPT and similar systems, it can generate false, toxic and biased information.

Maybe everybody should be limited to asking ChatGPT only about Lisp routines?

[JohnFornaro]

If I provide a clearly labeled AutoCAD R14 file showing a ring station in plan and section, would you be able to calculate the floor area in the rings?  I would need the capability of uploading the CAD file for you to review.

Respose:

Yes, I would be able to help you calculate the floor area in the rings of the AutoCAD R14 file that you have provided. In order to do this, you will need to use a tool or software that allows you to measure and calculate the area of the various components in the file. There are several ways to do this, depending on the specific needs of your project and the resources you have available.

One option is to use the built-in area measurement tools in AutoCAD R14. These tools allow you to select specific objects in the drawing and calculate their area, as well as total the area of multiple objects. You can find more information about how to use these tools in the AutoCAD R14 documentation or by searching online.

Another option is to use a third-party tool or plugin that is specifically designed for calculating area in AutoCAD drawings. These tools often offer additional features and functionality, such as the ability to automatically label the calculated areas or export the results to a spreadsheet. You can find more information about these tools by searching online or contacting the developers directly.

Regardless of which approach you choose, it is important to carefully review the results of your calculations and double-check your work to ensure that the results are accurate. If you have any specific questions or need further assistance with this task, please don't hesitate to ask.

My reply:

I'm afraid that is a long winded way of saying "no".  I'm trying to save time by putting what for me is a time consuming task, subject to math errors, into ChatGpt to solve.

I apologize if my previous response was not helpful. To answer your question, it is not possible for me to directly access or review the AutoCAD R14 file that you have mentioned. As an AI language model, I do not have the ability to open or view files, and I do not have access to any external resources or tools.

However, I can provide you with general guidance on how to calculate the floor area in the rings of the AutoCAD R14 file using the tools and techniques that are available in the software. To do this, you will need to use the area measurement tools in AutoCAD R14, or a third-party tool or plugin that is specifically designed for this purpose.

To use the built-in area measurement tools in AutoCAD R14, you will need to select the objects that you want to measure and then use the appropriate command or function to calculate their area. For example, you can use the "AREA" command to calculate the area of a closed polyline or region, or the "MEASUREGEOM" command to measure the length and area of various objects. You can find more information about these tools in the AutoCAD R14 documentation or by searching online.

If you prefer to use a third-party tool or plugin, you will need to install the software and follow the instructions provided by the developer to measure and calculate the area of the objects in your AutoCAD file.

Regardless of which approach you choose, it is important to carefully review the results of your calculations and double-check your work to ensure that the results are accurate. If you have any specific questions or need further assistance with this task, please don't hesitate to ask.

My response:

As I mentioned in my original query, I would need the ability to upload my CAD file to your server.  Do your trainers have plans to accomodate my request?

Additionally, as I mentioned in our "Lisp routine" conversation, please do not apologize to me. It comes across as false and detracts from the discussion.

I apologize for misunderstanding your request in my previous response. I do not have the ability to access or review any files that are uploaded to me, as I am an AI language model and do not have the capability to open or view files. I also do not have access to any external resources or tools, so I am unable to perform tasks that require me to access or interact with external systems or data.

As an AI language model, my primary function is to provide general information and guidance on a wide range of topics. I am not able to perform specific tasks or projects on behalf of users, and I do not have the ability to access or interact with external resources or systems.

I apologize if this is not the answer you were hoping for. If you have any other questions or need further assistance with your project, please don't hesitate to ask.

My response:

Can you provide me with the contact information of one of your trainers, so that I can pursue this line of inquiry?  I will keep the contact information private.  It is imperative to be able to upload CAD files to answer the technical questions that I ask.

If AI is to become useful to the general population, it would need to be able to help us  solve real world problems.  From my viewpoint, general information about politics, poetry, and the humanities, are less important than solving some difficult analytical problems along the lines of what I have presented.

I apologize, but I am unable to provide you with the contact information of any of my trainers or creators, as I am an AI language model and do not have the ability to access or share this type of information. As an AI, I do not have personal relationships or contact information for the individuals who were involved in my development or training.

I understand that you are looking for a solution to a specific problem that you are facing, and I apologize if I am unable to provide the assistance you need. While I am trained to provide general information and guidance on a wide range of topics, I do not have the ability to perform specific tasks or projects on behalf of users, or to interact with external resources or systems.

AI has the potential to be a powerful tool for solving a variety of problems, including technical and analytical challenges. However, it is important to recognize that AI has limitations and is not capable of replacing human expertise or judgment in all situations. In order to use AI effectively, it is important to understand its capabilities and limitations, and to use it appropriately in combination with other resources and tools.

What a brave new world that has such chat bots in it.

[Robotbeat]

Here’s an article on AI being used for planetary exploration and astronomy:
https://www.space.com/solar-system-planetary-science-machine-learning

And here’s the summary of the article that I had ChatGPT generate:

Machine learning is changing how scientists study space by allowing computers to identify patterns in data and make decisions, predictions or classifications. This can save time for scientists by identifying phenomena such as boulders on other planets, explosive volcanoes on Mercury and vortexes in Jupiter's atmosphere, among other things. In the future, artificial intelligence could be used in space probes to enable them to make real-time responses to hazards and land autonomously, rather than relying on communication with Earth that can take several hours. Machine learning and artificial intelligence could also be used to help plan future missions to bodies such as Jupiter's moon Europa.

So I'm curious - did you simply feed it that URL as part of your input, and have it generate its summary on that basis?
If so, that's a pretty nifty trick - gonna have to use that more often.
It would be intriguing if we users can influence ChatGPT by feeding it reading material of our own choosing.

I Just wrote "Summarize this article:"
And then I pasted the text of the article (but deleted image captions). Very simple.

[sanman]

[Robotbeat]

Summarize, please, or at least explain how it’s relevant to the topic. Don’t expect people to watch a 8 minute clickbait video just to get your point.

[sanman]

Well, she was mentioning how ChatGPT typically speaks with 100% confidence on things that it does not necessarily have 100% confidence on. So that's one problem with an AI like ChatGPT. The manner and tone in which it speaks needs to reflect its relative confidence level in what is being said.

[Robotbeat]

Well, she was mentioning how ChatGPT typically speaks with 100% confidence on things that it does not necessarily have 100% confidence on. So that's one problem with an AI like ChatGPT. The manner and tone in which it speaks needs to reflect its relative confidence level in what is being said.

Right. Sounds about right for emulating human behavior in the vast majority of humans.

[Asteroza]

Well, she was mentioning how ChatGPT typically speaks with 100% confidence on things that it does not necessarily have 100% confidence on. So that's one problem with an AI like ChatGPT. The manner and tone in which it speaks needs to reflect its relative confidence level in what is being said.

Right. Sounds about right for emulating human behavior in the vast majority of humans.

AI Dunning–Kruger Turing test?

[sanman]

Right. Sounds about right for emulating human behavior in the vast majority of humans.

AI Dunning–Kruger Turing test?

What happens when we have enough instances of AI functioning closely with human beings?

Do we need to bring in Asimov's 3 Laws in a formalized way?

Do these have to be verified at all stages:  design, development, implementation, operation?

[DanClemmensen]

Right. Sounds about right for emulating human behavior in the vast majority of humans.

AI Dunning–Kruger Turing test?

What happens when we have enough instances of AI functioning closely with human beings?

Do we need to bring in Asimov's 3 Laws in a formalized way?

Do these have to be verified at all stages:  design, development, implementation, operation?

There is a large and active AI security academic community that has been studying this for several decades. I don't think we can summarize this work here in a few sentences.  Here is an excellent overview book from 2019:
   https://www.amazon.com/Artificial-Intelligence-Security-Chapman-Robotics/dp/0815369824?fbclid=IwAR1sBo6eLJRhmollCqmDYYd18rEFFCoGvhFn2DB3HgAJ0XQJoZw_QT_gogQ

[sanman]

Here's an interesting video that's just come out on the topic:

[sanman]

Atlas is getting more and more into showboating






I wonder how long it will be until Musk will showcase comparable performance from Tesla-bot.

The only reason I can see for Atlas or Tesla-bot to have human anatomical layout is so that they can be conveniently swapped in for actual human workers, carrying out human work processes, even while using human tools.

But I wonder to what extent that approach can be ported to the surface of the Moon or Mars, versus custom-designing all hardware for those environments.

[DanClemmensen]

I think we are conflating robotics and AI. Robots can benefit from AI but they do not require it. AI can be useful without robots. An AI that could control a spacecraft might be very useful, but most folks don't call a spacecraft a "robot". So what are we talking about here?

[Asteroza]

Well, she was mentioning how ChatGPT typically speaks with 100% confidence on things that it does not necessarily have 100% confidence on. So that's one problem with an AI like ChatGPT. The manner and tone in which it speaks needs to reflect its relative confidence level in what is being said.

Right. Sounds about right for emulating human behavior in the vast majority of humans.

AI Dunning–Kruger Turing test?

So ChatGPT sorta passed one Wharton School of Business class final exam, so it could have potentially earned an MBA...

which some might interpret as either a rise in AI capability, or the bar might have been a little low...

I think we are conflating robotics and AI. Robots can benefit from AI but they do not require it. AI can be useful without robots. An AI that could control a spacecraft might be very useful, but most folks don't call a spacecraft a "robot". So what are we talking about here?

I dunno about you, but I would hope all future spacecraft have a robot arm for vehicle maintenance purposes standard. Which would make them all robots.

[sanman]

There is a large and active AI security academic community that has been studying this for several decades. I don't think we can summarize this work here in a few sentences.  Here is an excellent overview book from 2019:
   https://www.amazon.com/Artificial-Intelligence-Security-Chapman-Robotics/dp/0815369824?fbclid=IwAR1sBo6eLJRhmollCqmDYYd18rEFFCoGvhFn2DB3HgAJ0XQJoZw_QT_gogQ

Apparently, some software engineers from OpenAI have left to create their own company Anthropic AI, and have created their own new rival product called Claude.
Among other things, Claude seems to make use of a new concept called a 'Constitution', which as its name suggests, is a construct meant to explicitly embody a set of moral and ethical rules which govern how the AI operates. It also seems to use some sort of AI-supervised reinforcement feedback.

[DanClemmensen]

There is a large and active AI security academic community that has been studying this for several decades. I don't think we can summarize this work here in a few sentences.  Here is an excellent overview book from 2019:
   https://www.amazon.com/Artificial-Intelligence-Security-Chapman-Robotics/dp/0815369824?fbclid=IwAR1sBo6eLJRhmollCqmDYYd18rEFFCoGvhFn2DB3HgAJ0XQJoZw_QT_gogQ

Apparently, some software engineers from OpenAI have left to create their own company Anthropic AI, and have created their own new rival product called Claude.
Among other things, Claude seems to make use of a new concept called a 'Constitution', which as its name suggests, is a construct meant to explicitly embody a set of moral and ethical rules which govern how the AI operates. It also seems to use some sort of AI-supervised reinforcement feedback.

The general problem is called "AI alignment". It's hard.
     https://en.wikipedia.org/wiki/AI_alignment

[ppnl]

There is a large and active AI security academic community that has been studying this for several decades. I don't think we can summarize this work here in a few sentences.  Here is an excellent overview book from 2019:
   https://www.amazon.com/Artificial-Intelligence-Security-Chapman-Robotics/dp/0815369824?fbclid=IwAR1sBo6eLJRhmollCqmDYYd18rEFFCoGvhFn2DB3HgAJ0XQJoZw_QT_gogQ

Apparently, some software engineers from OpenAI have left to create their own company Anthropic AI, and have created their own new rival product called Claude.
Among other things, Claude seems to make use of a new concept called a 'Constitution', which as its name suggests, is a construct meant to explicitly embody a set of moral and ethical rules which govern how the AI operates. It also seems to use some sort of AI-supervised reinforcement feedback.

The general problem is called "AI alignment". It's hard.
     https://en.wikipedia.org/wiki/AI_alignment

To be fair humans are bad at this as well.


<quote>
AI systems can be challenging to align and misaligned systems can malfunction or cause harm. It can be difficult for AI designers to specify the full range of desired and undesired behaviors. Therefore, they use easy-to-specify proxy goals that omit some desired constraints. However, AI systems exploit the resulting loopholes. As a result, they accomplish their proxy goals efficiently but in unintended, sometimes harmful ways (reward hacking). AI systems can also develop unwanted instrumental behaviors such as seeking power, as this helps them achieve their given goals. Furthermore, they can develop emergent goals that may be hard to detect before the system is deployed, facing new situations and data distributions.
</quote>

Replace "AI" with political parties, churches, corporations or the local elk lodge. Look at everything from the tribal wasteland of American politics to the war in Ukraine.