ChatGPT on geoengineering

[Robert Chris]

I'm experimenting with ChatGPT.  I thought it might be interesting to
see what it has to say about geoengineering. Attached is the text.  For
those not yet familiar with ChatGPT, my questions (all quite short)
appear immediately after the RO logo. ChatGPT's response (all quite
long) appear immediately after the ChatGPT header.

I'm particularly interested in the arguments against geoengineering as
these tell us what we're up against and might help us in framing our
counterarguments more carefully.  The arguments in favour of
geoengineering might provide us with some useful phrases.  The question
in which I ask it to make a clearer distinction between GGR/CDR and
SRM/AE also offers some useful insights into the general confusion in
this area.

May just be a bit of fun, but if ChatGPT is drawing upon humanity's deep
fund of published material, it might also be a useful way of testing our
ideas to see whether we've pitched them well enough.

Regards

Robert

[Douglas Grandt]

Robert,

That ChatGPT thread exceeded may attention span by a favor of 2 or 3, so having seen one ray of light with this almost-but-not-quite definitive endorsement,

While reducing emissions and pursuing sustainable solutions are critical, it may also be necessary to explore additional strategies and approaches, such as carbon removal technologies or targeted interventions, to enhance the chances of avoiding the most severe impacts.

… I skipped to the end to see this:

In conclusion, the potential risks, uncertainties, and ethical issues associated with researching and developing solar radiation management technologies to increase Earth's albedo make it a risky and unwise approach to addressing global warming. Instead, efforts should be focused on reducing greenhouse gas emissions through a combination of technological innovation, policy changes, and societal shifts. By addressing the root cause of the problem, we can create a more sustainable, equitable, and resilient future for all.

Coincidentally, on Facebook this morning, I was asked: 

“What effect do you think Al will have on the efforts to mitigate and adapt?”

My reply was:

“Gary, none, because Al learns from past information, and past consensus is wrong when it comes to ocean-atmosphere equilibrium. E.g., IPCC "best climate science you've never heard of" coined by Mark Hertsgaard and Mike Mann versus 10°C "global warming in the pipeline" which run counter to each other.

“Concepts like "partial pressure" and

"saturation" which control oceanic CO2 absorption and out-gassing as well as and heat capacity, storage and transfer don't seem to be documented.

“If you know of papers that delve into equilibrium, please share.”

IMO your ChatGPT questions validated my response to my friend, Gary: vague, general and inconclusive. So I decided to do my own assessment, below, which is also totally general and inconclusive.

Doug: Which is correct? 1) Michael Mann’s “the best climate science you’ve never heard of”, or 2) Jim Hansen’s “global warming in the pipeline?” 

ChatGPT: Both statements are valid and convey important information about climate change.

Michael Mann is a climate scientist who has made significant contributions to the understanding of climate change. He is best known for his work on the "hockey stick graph," which shows the dramatic increase in global temperatures over the past century. Mann has also written about lesser-known aspects of climate science, such as the impact of ocean currents on global climate patterns. His statement "the best climate science you've never heard of" may refer to some of these less well-known aspects of climate research that are nonetheless crucial for understanding the full scope of climate change.

Jim Hansen is another prominent climate scientist who has been active in the study of climate change for decades. He is known for his early warnings about the dangers of global warming, including his famous 1988 testimony before the US Congress. Hansen's statement "global warming in the pipeline" refers to the idea that even if we were to stop emitting greenhouse gases today, there is still a significant amount of warming that is "in the pipeline" due to the gases that have already been emitted. This means that we must take action to reduce emissions immediately in order to avoid the worst impacts of climate change in the future.

Both Mann and Hansen have made important contributions to our understanding of climate change, and their statements highlight different aspects of this complex and urgent

That put the nail in the coffin for me.

Doug

Sent from my iPhone (audio texting)

On May 8, 2023, at 1:05 PM, Robert Chris <robert...@gmail.com> wrote:

I'm experimenting with ChatGPT.  I thought it might be interesting to see what it has to say about geoengineering. Attached is the text.  For those not yet familiar with ChatGPT, my questions (all quite short) appear immediately after the RO logo. ChatGPT's response (all quite long) appear immediately after the ChatGPT header.

--
You received this message because you are subscribed to the Google Groups "Planetary Restoration" group.
To unsubscribe from this group and stop receiving emails from it, send an email to planetary-restor...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/planetary-restoration/a2333e4e-de10-77c1-2bc7-a5c6ec098239%40gmail.com.

<ChatGPT on geoengineering.docx>

[John Nissen]

Hi Robert,

Thanks for sharing that with us.  It is interesting how able the software is to obtain the consensus views from different stand-points.  But it highlights the need to do quantitative analysis in order to arrive at viable solutions.  There is no model of the Earth System to work with. All the software can do is to analyse the responses of scientists to the observations of the Earth System and the modelling thereof, with all its weaknesses, hidden assumptions and political biases.

There is a bias towards accepting repeated text as being more authoritative.  Thus they repeat the mantra that we should "address the root cause" of climate change by reducing emissions as our primary focus, see Doug Grandt's email..

However the textual analysis has its uses.  It has thrown up a basic problem about the definition of tipping point.  Some people assume it is a threshold at which some process becomes irreversible.  Irreversibility depends on the tools and techniques available.  If we don't allow intervention, then we are probably past many tipping point thresholds already.  The term 'tipping point' is otherwise misleading, since it refers to processes exhibiting positive feedback without any threshold.  Positive feedback has been visible in many systems since around 1980, such as the retreat of the Arctic sea ice which is driven largely by albedo positive feedback.  I must make this clear in my letter to the Bulletin of Atomic Scientists, which we might discuss at the PRAG meeting which starts in just over half an hour.  The link is on one of PRAG meeting threads.

Cheers, John

--
You received this message because you are subscribed to the Google Groups "Healthy Planet Action Coalition (HPAC)" group.
To unsubscribe from this group and stop receiving emails from it, send an email to healthy-planet-action...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/healthy-planet-action-coalition/a2333e4e-de10-77c1-2bc7-a5c6ec098239%40gmail.com.
For more options, visit https://groups.google.com/d/optout.

[Douglas Grandt]

Errata 

“favor” should be “factor” in the opening sentence 

The final word “issue” inadvertently was not copied and pasted: “complex and urgent issue”

Doug

Sent from my iPhone (audio texting)

On May 8, 2023, at 3:21 PM, Douglas Grandt <answer...@mac.com> wrote:



[Bruce Melton -- Austin, Texas]

Robert, Thanks large, this is awesome.

And now I understand AI. It's a plagiaristic regurgitational machine that digests the world's known knowledge and spits out answers to questions using full sentences and classic writing formats. It appears to be weighted towards popular media reporting and policy, then consensus reporting, then science. What I do not see is any (significant) weighting towards advocacy, where the moral hazard is thriving. Thanks for doing this Robert. It is quite informative as to the average state of our global climate knowledge.

And I never thought I would be correcting AI, HAL. -- The repeated theme of carbon neutrality has not been accurate since AR5, but concepts were not too robust in AR5. In 2018, 1.5 C made it clear with requiring up to 1250+/- Gt atmospheric removal plus net zero mid-century and in AR6, SSP1-2.6 gave us CO2 a concentration falling to 430 ppm at 2100 after overshoot to 460 ppm mid-century. 

What is revealing is another repeated theme of "essential sustainability actions" centered around emissions reductions/cessation. After 30 years of sustainability action failure (much longer actually) AI can't figure out that this is bad?

Then there is the almost complete lack of discussion of tipping, well reflective of the consensus science.

The moral hazard is discussed in the bit "against" SRM using the normal responses.

And I was wondering why it had yet to cite the Precautionary Principle and it did in this final section - but only the interpretation that is used by those support moral hazard thinking, "The principle that the introduction of a new product or process whose ultimate effects are disputed or unknown should be resisted," (Oxford), and the greater interpretation is ignored as usual, "Where there are threats of serious or irreversible damage, lack of full scientific certainty shall not be used as a reason for postponing cost-effective measures to prevent environmental degradation." (Rio '92)

So how long did all this take Robert and can I publish it on Climate Discovery? It is quite a good summary for legacy climate culture (which is quite dangerous in general), but I think most importantly it is illustrative of what is wrong with our climate culture today in Climate Change 2.0 after tipping has activated.

Thanks again,

Bruce M

Bruce Melton PE
Director, Climate Change Now Initiative, 501c3
President, Melton Engineering Services Austin
8103 Kirkham Drive
Austin, Texas 78736
(512)799-7998
ClimateDiscovery.org
ClimateChangePhoto.org
MeltonEngineering.com
Face...@Bruce.Melton.395
Inst...@Bruce.C.Melton
The Band Climate Change
Twitter - BruceCMelton1

[Robert Chris]

Bruce

Glad you liked it. I commented elsewhere that we'll know when we're winning because then ChatGPT will be spitting our answers that we agree with.

In answer to your two questions, scarily this whole thing took less than 30 minutes.  It might be derivative garbage but it's very fast derivative garbage!

Also note its answer to my question about which was the better of the two replies it gave in support of and against geoengineering.  This is crucially important.

By all means post it but when doing so, please ensure that it is clear that this was an unstructured experiment and that the results should be understood to reflect an orthodox and highly contested understanding based on data up to and including 2021.

I should also add that in other subject areas, in particular my quest for some fluid dynamics input to a water feature I'm designing for my terrace, I got a series of answers and when I repeatedly asked 'Are you sure' it came back and very politely apologised for an error in its earlier responses.  After asking a series of questions, it finally said I should seek the advice of someone experienced designing fountains!

Regards

Robert

[Sev Clarke]

Hi Robert,

This is indeed a useful exercise you have performed with ChatGPT as it captures, as no other method does, many of the fallacies and muddled thinking that we are contesting.
Attached are my comments, corrections and additions to the ChatGPT responses to your requests. I trust that they will help our HPAC, PRAG and NOAC groups correct some of the muddled thinking and practices that are extant.

[Bruce Melton -- Austin, Texas]

Robert,

Thirty minutes to assimilate the total world knowledge... -bwuh... I am looking forward to quizzing it about tipping.

&&& I have your caveat for my post, good deal. Thanks.

What is your interpretation of the two responses about geoengineering -in support of and against? I didn't analyze those two too deeply, it all seemed like a blur of money shots from so many popular press articles. I do recall "against" seemed like an emotional response, or rather a regurgitation of emotional responses. It was also interesting when the "against" query stalled, and when you asked again it came back in a format different from all the rest.

And btw, my research was in nonpoint source stormwater runoff pollution treatment technologies. I designed, built and studied several water features or wetponds as we have labelled them in the biz. Love to hear about your project and maybe I can help. Let's take it private if you want to discuss further.

Like a duck,

B

Bruce Melton PE
Director, Climate Change Now Initiative, 501c3
President, Melton Engineering Services Austin
8103 Kirkham Drive
Austin, Texas 78736
(512)799-7998
ClimateDiscovery.org
ClimateChangePhoto.org
MeltonEngineering.com
Face...@Bruce.Melton.395
Inst...@Bruce.C.Melton
The Band Climate Change
Twitter - BruceCMelton1

[Dr. Robert Chris]

Piece in The Conversation today about ChatGPT fits nicely with our discussion.

Regards

Robert

Cheers,
Sev  

 wrote:

I'm experimenting with ChatGPT.  I thought it might be interesting to see what it has to say about geoengineering. Attached is the text.  For those not yet familiar with ChatGPT, my questions (all quite short) appear immediately after the RO logo. ChatGPT's response (all quite long) appear immediately after the ChatGPT header.

I'm particularly interested in the arguments against geoengineering as these tell us what we're up against and might help us in framing our counterarguments more carefully.  The arguments in favour of geoengineering might provide us with some useful phrases.  The question in which I ask it to make a clearer distinction between GGR/CDR and SRM/AE also offers some useful insights into the general confusion in this area.

May just be a bit of fun, but if ChatGPT is drawing upon humanity's deep fund of published material, it might also be a useful way of testing our ideas to see whether we've pitched them well enough.

Regards

Robert

-- 
You received this message because you are subscribed to the Google Groups "Planetary Restoration" group.
To unsubscribe from this group and stop receiving emails from it, send an email to planetary-restor...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/planetary-restoration/a2333e4e-de10-77c1-2bc7-a5c6ec098239%40gmail.com.
<ChatGPT on geoengineering.docx>

[Douglas Grandt]

⚠️ TODAY’S WORDLE ALERT ⚠️

A fun little experiment involving today’s Wordle, and ChatGPT made a couple not-so-startling honest admissions:

Me: Write a sentence about a real plausible hypothetical situation involving donald trump using these five worlds in this order: arose story sworn scorn shorn

ChatGPT: In a bizarre turn of events, a peculiar arose story of Donald Trump being sworn in as the leader of a tiny nation, despite the widespread scorn and disdain from the international community, leaving him shorn of his former political power.

Me: Is this statement a true to life hypothetical but plausible scenario?

ChatGPT: No, the statement I provided is purely fictional and hypothetical. As of my last knowledge update in September 2021, there have been no real-life scenarios involving Donald Trump being sworn in as the leader of a different country or being shorn of his political power in such a manner.

More like obfuscation from a devious politician’s non-answer to a reporter’s tough question.

Grade: F (let me count the ways)

Seriously!

Doug

Sent from my iPhone (audio texting)

On May 18, 2023, at 9:34 AM, Ye Tao <t...@rowland.harvard.edu> wrote:



The author states (likely wrong) assumptions as if they were facts:

"My bet, then, is that as we learn more about the brain’s detailed workings, we will precisely identify which areas of the brain embody consciousness. This is because those regions will exhibit behaviour that can’t be explained by currently known chemistry and physics. Already, some neuroscientists are seeking potential new explanations for consciousness to supplement the basic equations of physics.

While the processing of LLMs is now too complex for us to fully understand, we know that it could in principle be predicted from known physics. On this basis, we can confidently assert that ChatGPT is not conscious.

"

Hence the conclusion that ChatGPT is not conscious cannot be arrived at through the flawed reasoning provided.  

I had 3 groups of experimental neural scientists as colleagues at the Rowland Institute.  Everything I heard and saw up to 2021 in single-cell-resolution whole brain imaging in Zebra fish, fruit flies, and partial-brain single-cell-resolution mouse models suggests deterministic relationships among biochemical firing of neuron (and networks of neurons), sensation, and decision making.   The world appears very much deterministic.

Ye

You received this message because you are subscribed to the Google Groups "NOAC Meetings" group.
To unsubscribe from this group and stop receiving emails from it, send an email to noac-meeting...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/noac-meetings/d7feed03-fa9c-21cc-5ad1-a487f25e4143%40gmail.com.

--
You received this message because you are subscribed to the Google Groups "Healthy Planet Action Coalition (HPAC)" group.
To unsubscribe from this group and stop receiving emails from it, send an email to healthy-planet-action...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/healthy-planet-action-coalition/0db986b5-f972-d80c-eea4-432c75274598%40rowland.harvard.edu.

[Ye Tao]

The author states (likely wrong) assumptions as if they were facts:

"My bet, then, is that as we learn more about the brain’s detailed workings, we will precisely identify which areas of the brain embody consciousness. This is because those regions will exhibit behaviour that can’t be explained by currently known chemistry and physics. Already, some neuroscientists are seeking potential new explanations for consciousness to supplement the basic equations of physics.

While the processing of LLMs is now too complex for us to fully understand, we know that it could in principle be predicted from known physics. On this basis, we can confidently assert that ChatGPT is not conscious.

"

Hence the conclusion that ChatGPT is not conscious cannot be arrived at through the flawed reasoning provided.  

I had 3 groups of experimental neural scientists as colleagues at the Rowland Institute.  Everything I heard and saw up to 2021 in single-cell-resolution whole brain imaging in Zebra fish, fruit flies, and partial-brain single-cell-resolution mouse models suggests deterministic relationships among biochemical firing of neuron (and networks of neurons), sensation, and decision making.   The world appears very much deterministic.

Ye

On 5/18/2023 8:59 AM, Dr. Robert Chris wrote:

You received this message because you are subscribed to the Google Groups "NOAC Meetings" group.
To unsubscribe from this group and stop receiving emails from it, send an email to noac-meeting...@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/noac-meetings/d7feed03-fa9c-21cc-5ad1-a487f25e4143%40gmail.com.