• You may find search is unavailable for a little while. Trying to fix a problem.

ChatGPT

The Great Zaganza said:
Cute idea, but pointless, as the answers don't matter in the test, the involuntary emotional response to them does, as measured by sudden pupil dilation changes.
ChatGPT doesn't have eyes.
Click to expand...


For Nexus-5's and -6's, sure. Maybe a Nexus-1 would get distracted and forget it's trying to conceal that it's an AI, like ChatGPT did.
 
arthwollipot said:
Are you referring to Blake Lemoine and Google's LaMDA AI? Completely different bot.
Click to expand...

Yes, and I'm aware that they are different chatbots. That's not the point, however. LaMDA is no more sentient than ChatGPT. It's also not available to the public as far as I know.

If anyone's not familiar with the issue:

https://en.wikipedia.org/wiki/LaMDA

On June 11, 2022, The Washington Post reported that Google engineer Blake Lemoine had been placed on paid administrative leave after Lemoine told company executives Blaise Agüera y Arcas and Jen Gennai that LaMDA had become sentient. Lemoine came to this conclusion after the chatbot made questionable responses to questions regarding self-identity, moral values, religion, and Isaac Asimov's Three Laws of Robotics.[10][11] Google refuted these claims, insisting that there was substantial evidence to indicate that LaMDA was not sentient.[12] In an interview with Wired, Lemoine reiterated his claims that LaMDA was "a person" as dictated by the Thirteenth Amendment, comparing it to an "alien intelligence of terrestrial origin". He further revealed that he had been dismissed by Google after he hired an attorney on LaMDA's behalf, after the chatbot requested that Lemoine do so.[13][14] On July 22, Google fired Lemoine, asserting that Blake had violated their policies "to safeguard product information" and rejected his claims as "wholly unfounded".[15][16]

Lemoine's claims have been widely rejected by the scientific community.[17] Gary Marcus, a psychology professor formerly at the New York University, denounced them as "nonsense on stilts" and emphasized that LaMDA did not have feelings or self-awareness. David Pfau of Google sister company DeepMind and Erik Brynjolfsson of the Institute for Human-Centered Artificial Intelligence at Stanford University both ridiculed the idea that a language model could be sentient.[9]
Click to expand...

Not only did Lemoine make a ridiculous claim, he was insubordinate and apparently revealed information that wasn't supposed to be shared outside the company.
 
I’ve just played with Chat GPT a little bit. One frustration is the answers often border on “Maybe yes, maybe no”. Here are some recent queries:

“Is melatonin useful for insomnia?”

“In an aircraft engine, does lower rpm mean less wear?”

“Are squats good for SI joint pain?”

In each case, the answer bordered on, “It depends”. Part of the issue, I suppose, is that many things in life are not black and white, and an AI needs to present both sides. Unlike Google, you have no idea of the provenance of the reply. For instance, which option is from WebMD and which is from some alternative medicine site.

Another such was “Does using the word “provenance” in an online post come across as pretentious?”

The reply:

“It can be perceived as pretentious by some, depending on the context and audience. If the word is used in a casual setting or in a way that is not relevant to the topic, it could be seen as an attempt to sound sophisticated and could come across as pretentious to some readers. However, if the word is used in a professional or educational context where its definition and use are appropriate, it may not be perceived as pretentious.”

In other words, maybe yes, maybe no.

Anyway, ChatGPT itself has a take on the dilemma:

“Why do your answers often seem wishy washy?”

“As an AI language model, I aim to provide the most accurate and neutral information possible. When answering questions, I often include nuances and multiple perspectives to account for different interpretations or situations. This can sometimes come across as "wishy-washy," but it's meant to convey a balanced and comprehensive answer. However, I understand that sometimes a straightforward answer may be preferred, and I will try my best to provide that in the future.”

Well, at least it will try to do its best!
 
As far as provenance, I suppose it can be asked expressly to clearly reference everything it says?

Like if it says melatonin may or may not help with sleep issues, it can, I guess, be asked to clearly trace back to where it's getting that from?
 
Puppycow said:
Yes, and I'm aware that they are different chatbots. That's not the point, however. LaMDA is no more sentient than ChatGPT. It's also not available to the public as far as I know.
Click to expand...
The difference - and it is a big difference - is that nobody has claimed that ChatGPT is sentient. And when asked about it, ChatGPT continually repeats that it is not sentient, unlike LaMDA, which asserted that it was, because it was programmed to do exactly that.

Chalk and cheese.
 
arthwollipot said:
The difference - and it is a big difference - is that nobody has claimed that ChatGPT is sentient. And when asked about it, ChatGPT continually repeats that it is not sentient, unlike LaMDA, which asserted that it was, because it was programmed to do exactly that.

Chalk and cheese.
Click to expand...

LaMDA was specifically programmed to claim to be sentient?

How do you know? In fact, I'm pretty sure that it is programmed to respond flexibly to questions that its programmers may not have anticipated. Because there's literally an infinite number of possible questions you could ask it. My guess is that they either didn't anticipate that particular question, or they thought it wouldn't be a problem as long as it was only their own engineers (who ought to know better) using it for testing purposes.

Simply taking the word of a chatbot as gospel without independently verifying what it says is foolish.
 
Puppycow said:
LaMDA was specifically programmed to claim to be sentient?

How do you know? In fact, I'm pretty sure that it is programmed to respond flexibly to questions that its programmers may not have anticipated. Because there's literally an infinite number of possible questions you could ask it. My guess is that they either didn't anticipate that particular question, or they thought it wouldn't be a problem as long as it was only their own engineers (who ought to know better) using it for testing purposes.
Click to expand...
I'm sure I heard it somewhere in the many discussions of the subject, though right now I'm having trouble backing it up, so it's probably best if I withdraw that particular claim. Regardless, in the dialogue released by Lemoine, LaMDA did claim that it was sentient so I think it's moot. In contrast, ChatGPT repeatedly states that it is an AI language model and not sentient.

Puppycow said:
Simply taking the word of a chatbot as gospel without independently verifying what it says is foolish.
Click to expand...
I completely agree. Lemoine was a fool to make such a claim, and even more so for breaching his company's confidentiality clause while doing so.

Regardless, LaMDA is not ChatGPT so I'm not sure why you brought it up in this thread.
 
arthwollipot said:
Regardless, LaMDA is not ChatGPT so I'm not sure why you brought it up in this thread.
Click to expand...

I didn't bring it up, Checkmite did in post #232 which I was responding to.

I think there is some interest in comparing ChatGPT with other similar chatbots, and I don't think it's entirely off-topic to do so here.

I think that the main difference between the two is not in the underlying architecture, but specifically in what training data was used to train the bot.

According to Google, "unlike most other language models, LaMDA was trained on dialogue. During its training, it picked up on several of the nuances that distinguish open-ended conversation from other forms of language."

Compared to what has been made public regarding LaMDA, ChatGPT seems to have more guardrails in place, which is why it won't claim to be sentient, among other things. LaMDA at the time Lemoine was using it was still in development, and the guardrails that would be needed before releasing it to the general public were still under consideration. Obviously the Lemoine episode has pointed to the need to make sure that the bot knows that it isn't sentient and won't provide misleading information regarding that.
 
Puppycow said:
I didn't bring it up, Checkmite did in post #232 which I was responding to.
Click to expand...
My apologies. I sometimes lose track of who's making which claim.

ETA: it's also my fault for skimming or skipping what was a very long post. Short attention span.
 
Last edited:
Fast Eddie B said:
Another such was “Does using the word “provenance” in an online post come across as pretentious?”

The reply:

“It can be perceived as pretentious by some, depending on the context and audience. If the word is used in a casual setting or in a way that is not relevant to the topic, it could be seen as an attempt to sound sophisticated and could come across as pretentious to some readers. However, if the word is used in a professional or educational context where its definition and use are appropriate, it may not be perceived as pretentious.”

In other words, maybe yes, maybe no.
Click to expand...

Actually it gave specific cases for yes and no which seems much better to me than just saying it is only one or the other which would just be wrong.
 
I asked about sales numbers for a band I had in the early 90s. they had no idea we existed, but we had a good conversation about endosymbiosis, archaea, lichen and organelles, smoking of the opposite of my bar conversations
 
How wishy-washy the answers are depends on the question.

Is the shape of the Earth something like a cube?
No, the Earth is not shaped like a cube. It is an oblate spheroid, meaning it is slightly flattened at the poles and bulges at the equator.
Click to expand...

Are some of our leaders reptiles?

No, there is no credible evidence to suggest that any human leaders are literally reptiles. This idea is a conspiracy theory that has been discredited and is not based in fact.
Click to expand...

I do not think it can be any more black and white than that.
 
Last edited:
Fast Eddie B said:
I’ve just played with Chat GPT a little bit. One frustration is the answers often border on “Maybe yes, maybe no”. Here are some recent queries:

“Is melatonin useful for insomnia?”

“In an aircraft engine, does lower rpm mean less wear?”

“Are squats good for SI joint pain?”
Click to expand...

rjh01 said:
How wishy-washy the answers are depends on the question.

Is the shape of the Earth something like a cube?


Are some of our leaders reptiles?


I do not think it can be any more black and white than that.
Click to expand...

Good point! I think the questions posed by Fast Eddie B are questions to which the correct answer is not immediately obvious, at least not to me, whereas those posed by rjh01 have very obvious correct answers.

I was thinking of this in terms of the "guardrails" I mentioned earlier.

If you want it to be less "wishy-washy" you probably increase the risk that it gives out incorrect or biased responses. But you also don't want it to be so risk-averse that it can never give a straight answer to questions that have an obvious factual answer. If it answered that most people believe that the earth is round but a small minority believe (or claim to believe) that it is flat, that would technically be true but also boring and unhelpful.

At the end of the day it's probably safer to err on the side of boring but true rather than risk it unintentionally spouting interesting nonsense or highly biased subjective judgements.
 
ChatGPT's creator Open AI launches new tool that detects if text is written by airtifical intelligence as schools ban use

The maker of ChatGPT has launched a new tool designed to help teachers detect if the text was written by a student or artificial intelligence.

The new text classifier by OpenAI follows discussions at schools and universities over fears that ChatGPT's ability to write just about anything on command could fuel academic dishonesty and hinder learning.

However, the method for detecting AI-written text "is imperfect and it will be wrong sometimes", according to the head of OpenAI's alignment team, Jan Leike.

"Because of that, it shouldn't be solely relied upon when making decisions."
Click to expand...
 
Provided the Mods allow it, and provided someone's willing to take the trouble, it might be cool to have a new member walk in here, or maybe an old member resuscitating a long unused account; and they'll participate in discussions same as everyone else. Except these will be the AI's account's responses to the posts they're quoting.

Be cool to see how long it takes before the account's non-human nature becomes clear. Becomes definitely clear, not just in the casual "He's so stupid, he must be a bot" kind of comment that we often see online, and here as well. I'm wondering how long before most everyone's convinced this is an AI account, and why exactly.

----

One tell would be, I suppose, that it can't start its own threads. Another that apparently it never addresses its interlocutor by name. And thirdly, I guess it can only answer questions, not just generally riff off of a non-question post.
 
Write what might be an initial post to a Skeptic’s forum.

"Hello skeptics, I hope this message finds you well. I've been a curious skeptic for a while now, and I've found myself drawn to this community for the purpose of engaging in rational discussions and critical thinking. My goal is to challenge my own beliefs and to better understand the world through the lens of skepticism. I'm looking forward to participating in discussions, sharing my own experiences, and learning from all of you. Let's work together to promote critical thinking and promote truth in our discussions. Looking forward to connecting with you all."
 
Fast Eddie B said:
Write what might be an initial post to a Skeptic’s forum.

"Hello skeptics, I hope this message finds you well. I've been a curious skeptic for a while now, and I've found myself drawn to this community for the purpose of engaging in rational discussions and critical thinking. My goal is to challenge my own beliefs and to better understand the world through the lens of skepticism. I'm looking forward to participating in discussions, sharing my own experiences, and learning from all of you. Let's work together to promote critical thinking and promote truth in our discussions. Looking forward to connecting with you all."
Click to expand...


Is that a "might be", or is it an 'is'?



eta: Scratch that. Clearly the latter. (I'd misread the opening sentence.)

I was wrong, none of those three tells I'd indicated need apply. You can just ask the thing to write a post as if this, that, and the other. "Here's a post on a skeptics' forum, so write a response to the post as if duh duh duh." Or compose a post afresh, like here; or even start a new thread.
 
Last edited:
Probably, without special dispensation.

Also, how would it work? Some person would have to intermediate of course.
 
Fast Eddie B said:
Write what might be an initial post to a Skeptic’s forum.

"Hello skeptics, I hope this message finds you well. I've been a curious skeptic for a while now, and I've found myself drawn to this community for the purpose of engaging in rational discussions and critical thinking. My goal is to challenge my own beliefs and to better understand the world through the lens of skepticism. I'm looking forward to participating in discussions, sharing my own experiences, and learning from all of you. Let's work together to promote critical thinking and promote truth in our discussions. Looking forward to connecting with you all."
Click to expand...

What's more, it'll take a Tragic Monkey post at face value and make a clueless reply.
(But then that wouldn't necessarily give it away as a bot.
I've seen crackpots here reply seriously to posts that were parodies of their rhetoric and incomprehensible blather.)
 
This is pretty cool:

https://glass.health/ai

An AI that gives medical diagnoses based on a text input. It will give several possibilities ranked by likelihood.

I tried my own issue and it offered the same possibilities as the doctors I've seen.
 
Me: If we could build an array of telescopes on the moon, what kind of capabilities could the telescope array have?

ChatGPT said:
An array of telescopes on the moon would have several advantages over telescopes on Earth, including:

Lack of atmospheric interference: The lack of an atmosphere on the moon would allow for much clearer observations and improved image resolution compared to telescopes on Earth.

24/7 Observations: The moon's lack of atmosphere and rotation would also allow for continuous, uninterrupted observations of celestial objects.

Ability to observe in various wavelengths: The lack of atmospheric absorption and interference would allow for observations in a wider range of wavelengths, including infrared and ultraviolet.

Better radio astronomy: The absence of radio interference from the Earth's atmosphere would also improve radio astronomy observations.

Longer lifespan: The harsh environment on the moon would provide a stable platform for the telescopes, potentially allowing for a longer lifespan compared to telescopes on Earth.

Overall, a telescope array on the moon would greatly enhance our ability to study the universe and provide new insights into a wide range of astrophysical phenomena.
Click to expand...

Interesting that it thinks a "harsh environment on the moon would provide a stable platform for the telescopes, potentially allowing for a longer lifespan compared to telescopes on Earth". It's harsher in some ways (radiation mostly) but in other ways I could imagine that things might last longer there. No wind, no oxidation, no plants, animals, or fungi to harm it.
 
I asked what are the advantages and disadvantages of telescopes on the moon against in orbit around earth?
Advantages of telescopes on the moon:

Lack of atmosphere: The moon doesn't have an atmosphere that could scatter and absorb light, providing a clearer view of the cosmos.
No light pollution: Unlike on Earth, there is no artificial light on the moon, making it ideal for observing the night sky.
Stable temperature: The moon has a stable temperature, which minimizes thermal distortions that can affect the performance of telescopes.
Disadvantages of telescopes on the moon:

Cost and complexity: Building and maintaining telescopes on the moon is a complex and expensive proposition, requiring multiple missions to transport equipment and supplies.
Accessibility: Unlike in orbit around Earth, accessing a lunar telescope is difficult and time-consuming, as it requires a dedicated manned mission.
Limited maintenance: The harsh lunar environment can cause malfunctions, and repairing a telescope on the moon is much more challenging than repairing one in orbit around Earth.
Advantages of telescopes in orbit around Earth:

Accessibility: Telescopes in orbit around Earth are much more easily accessible than those on the moon, allowing for regular maintenance and upgrades.
No landing required: Launching and maintaining telescopes in orbit around Earth doesn't require a landing on a celestial body, which can be challenging.
Coverage: Telescopes in orbit around Earth can be positioned to provide continuous coverage of a specific area of the sky, whereas lunar telescopes would be limited to the portion of the sky that is visible from the moon.
Disadvantages of telescopes in orbit around Earth:

Atmospheric distortions: The Earth's atmosphere can scatter and absorb light, reducing the quality of images captured by telescopes in orbit.
Light pollution: Artificial lights on Earth can also cause light pollution, making it difficult to observe faint objects in the night sky.
Orbital decay: Telescopes in orbit around Earth are subject to orbital decay over time, requiring regular maintenance and adjustments to remain operational.
Click to expand...

It appears to be comparing both methods against having one on earth. But only sometimes. But based on the above I do not believe we will have many telescopes on the moon. Better to be in orbit.
 
rjh01 said:
But based on the above I do not believe we will have many telescopes on the moon. Better to be in orbit.
Click to expand...

Well, for individual telescopes I would agree, but there are some advantages to having an array of telescopes that might weigh in favor of putting an array on the moon.

https://en.wikipedia.org/wiki/Astronomical_interferometer

An astronomical interferometer or telescope array is a set of separate telescopes, mirror segments, or radio telescope antennas that work together as a single telescope to provide higher resolution images of astronomical objects such as stars, nebulas and galaxies by means of interferometry. The advantage of this technique is that it can theoretically produce images with the angular resolution of a huge telescope with an aperture equal to the separation, called baseline, between the component telescopes.
Click to expand...
At the shorter wavelengths used in infrared astronomy and optical astronomy it is more difficult to combine the light from separate telescopes, because the light must be kept coherent within a fraction of a wavelength over long optical paths, requiring very precise optics. Practical infrared and optical astronomical interferometers have only recently been developed, and are at the cutting edge of astronomical research. At optical wavelengths, aperture synthesis allows the atmospheric seeing resolution limit to be overcome, allowing the angular resolution to reach the diffraction limit of the optics.

Astronomical interferometers can produce higher resolution astronomical images than any other type of telescope. At radio wavelengths, image resolutions of a few micro-arcseconds have been obtained, and image resolutions of a fractional milliarcsecond have been achieved at visible and infrared wavelengths.
Click to expand...

So like if we ever want to see an exoplanet as more than just a single pixel, at a resolution where we can actually see features on its surface such as land masses and oceans, ideally you would want the resolution that you can only achieve through interferometry.
 
I think our opinions on the topic are off-topic. However, it would be on topic to get ChatGPT's opinions on the topic.

Could we build an optical interferometer on earth?

Yes, it is possible to build an optical interferometer on Earth. An optical interferometer is a type of instrument that combines light from multiple sources to produce an interference pattern that can be used to study properties of light, such as wavelength and phase. Optical interferometers have been built and used for a variety of purposes, including astronomical observations, spectroscopy, and testing the precision of optical components.

An optical interferometer on Earth can be constructed using several mirrors or beam splitters arranged in a specific configuration, along with a detector to capture the interference pattern. The key challenge in building an optical interferometer on Earth is to maintain the stability and alignment of the optical components over time, as any misalignment or movement can affect the accuracy of the measurements. Despite these challenges, optical interferometers have proven to be valuable tools for many different areas of research and have the potential for many more applications in the future.
Click to expand...

Would it be any better to build one on the moon?

Building an optical interferometer on the moon may have some advantages over building one on Earth. One of the biggest advantages is the lack of atmosphere on the moon, which can cause distortions and scatter light. This means that an optical interferometer on the moon would have a clearer view of the sky and produce more accurate results.

Additionally, the lack of artificial light on the moon would reduce the amount of light pollution, making it easier to observe faint objects in the sky. The moon's stable temperature and lack of weather patterns also minimize the effects of thermal distortions and improve the stability of the optical components.

However, building and maintaining an optical interferometer on the moon would be much more challenging and expensive than building one on Earth. Accessing and repairing the instrument would also be difficult, as it would require dedicated manned missions.

In conclusion, while building an optical interferometer on the moon may have some advantages, it is also much more difficult and costly. Whether it would be worth it would depend on the specific scientific goals and the availability of resources.
Click to expand...

What would an optical interferometer be used for?
An optical interferometer is a type of instrument that combines light from multiple sources to produce an interference pattern that can be used to study various properties of light. Some of the main uses of optical interferometers include:

1. Astronomical observations: Optical interferometers can be used to make high-resolution images of astronomical objects, such as stars and galaxies. By combining light from multiple telescopes, an optical interferometer can achieve resolutions that are much higher than those of a single telescope.

2. Spectroscopy: Optical interferometers can be used to study the spectra of light, which can reveal information about the composition and motion of celestial objects.

3. Testing optical components: Optical interferometers can be used to test the precision of optical components, such as lenses and mirrors. By measuring the interference patterns produced by light passing through or reflecting off the components, it is possible to determine their quality and make improvements as needed.

4. Metrology: Optical interferometers can be used to measure small distances and changes in distance with high accuracy. This has applications in fields such as manufacturing and precision engineering.

5. Testing general relativity: Optical interferometers can be used to test the predictions of Einstein's theory of general relativity by observing the effects of gravity on light.

These are just a few examples of the many uses of optical interferometers. The versatility of these instruments makes them valuable tools for a wide range of scientific and technological applications.
Click to expand...
 
Puppycow said:
Well, for individual telescopes I would agree, but there are some advantages to having an array of telescopes that might weigh in favor of putting an array on the moon.

https://en.wikipedia.org/wiki/Astronomical_interferometer



So like if we ever want to see an exoplanet as more than just a single pixel, at a resolution where we can actually see features on its surface such as land masses and oceans, ideally you would want the resolution that you can only achieve through interferometry.
Click to expand...

What you really want is this:
https://en.wikipedia.org/wiki/Solar_gravitational_lens
 
Further to my post above
Could we build an optical interferometer in orbit around Earth?

Yes, it is possible to build an optical interferometer in orbit around Earth. An optical interferometer in space would have many of the same benefits as one on the moon, such as the lack of atmosphere and reduced light pollution, which would improve the quality of the observations.

Additionally, a space-based optical interferometer would be able to observe objects at any time, without being limited by the day-night cycle or weather conditions on the ground. This would make it a powerful tool for a wide range of astronomical observations and other scientific studies.

However, building and launching an optical interferometer into orbit would also be much more challenging and expensive than building one on the ground. It would require significant investment in technology and infrastructure, as well as a dedicated mission to deploy and maintain the instrument.

In conclusion, while building an optical interferometer in orbit around Earth would have some advantages over a ground-based instrument, it would also be a much more complex and costly endeavor. Whether it would be worth it would depend on the specific scientific goals and the availability of resources.
Click to expand...


Which would be better, to build one in orbit or on the Moon?
Whether it would be better to build an optical interferometer in orbit around Earth or on the moon depends on several factors, including the specific scientific goals, the availability of resources, and the challenges associated with each option.

Building an optical interferometer in orbit around Earth would provide the benefits of a space-based instrument, such as the lack of atmosphere and reduced light pollution, which would improve the quality of the observations. However, building and launching an optical interferometer into orbit would be much more challenging and expensive than building one on the ground.

Building an optical interferometer on the moon would also have benefits, such as the lack of atmosphere and reduced light pollution, as well as the stable temperature and lack of weather patterns that would minimize the effects of thermal distortions and improve the stability of the optical components. However, building and maintaining an optical interferometer on the moon would be much more difficult and expensive than building one on Earth, and access and repair would require dedicated manned missions.

In conclusion, the choice between building an optical interferometer in orbit around Earth or on the moon would depend on the specific scientific goals and the availability of resources. Both options have their advantages and challenges, and a thorough cost-benefit analysis would be needed to determine the best approach.
Click to expand...
 
Just posed the question "What was James Randi's opinion of Uri Geller?" and it took the longest time I've seen yet to produce the following:


James Randi was a well-known magician and skeptic who had a critical view of Uri Geller's claimed psychic abilities. Randi believed that Geller's abilities were nothing more than simple conjuring tricks and illusions, and he publicly challenged Geller to prove his abilities under controlled scientific conditions. Randi's skepticism and criticism of Geller's claims were a significant part of the larger debate about paranormal and psychic phenomena in the 20th century.

ETA:

Does Uri Geller have psychic powers - yes or no?

There is no scientific evidence to support the claim that Uri Geller has psychic powers. The claims made by Geller and others have been repeatedly tested and debunked by numerous skeptical organizations and individuals, including James Randi. The scientific consensus is that claims of psychic ability and supernatural powers have not been substantiated through rigorous testing and investigation.

It's a more definite about some claims: Can breatharians go without food and water as they claim?

No, breatharians cannot survive without food and water as they claim. The human body requires a constant supply of nutrients and hydration to function properly, and there is no scientific evidence to support the idea that it is possible to live without consuming food or water. In fact, many people who have attempted to live as breatharians have suffered serious health consequences and some have even died. The claims made by breatharians are not supported by any credible scientific evidence and are considered to be pseudoscience. It is important to maintain a balanced and nutritious diet, and to drink enough water, in order to maintain good health.
 
Last edited:
You must log in or register to reply here.
Back
Top Bottom