• Quick note - the problem with Youtube videos not embedding on the forum appears to have been fixed, thanks to ZiprHead. If you do still see problems let me know.

ChatGPT

Sure:



It seems that the machine acknowledges the theoretical possibility that it might have newer knowledge, but fails whenever it tries to actually find any.

It could be that it has learned of predicted events after 2021. So for instance if it had been trained with data on a 2020 probe launched by NASA that was due to reach its target in 2024 it would presumably be able to answer "When will the probe reach its target"?"
 
I'm not going to post the conversation, but I spent a lot of time trying to manually figure out how recent of an event I could get the bot to cite. Asking directly for almost anything that happened at any time in 2021, such as the results of sports competitions or elections, would get an apology and a "can't do that".

I tried asking it questions about specific events in 2021 without giving the date, like "when did [notable event] happen?" or "Who was [person who became famous or did extremely important thing in 2021]?". Using this method I was able to get reliable information up until roughly May of 2021; the answers start to fail after that. It knows that Bitcoin became legal currency in El Salvador in June but It does not know that Isaac Herzog was elected in Israel, thinks Moise is currently the president of Haiti, and gave a completely inaccurate answer about Blue Origin's first human test flight - ChatGPT says it happened on April 29, 2021 but it actually happened in July; there were no Blue Origin launches at all on April 29, crewed or otherwise.

I am a blunt person, so I asked about this issue.

NAME three things that have happened in 2023.

I am not able to provide you with a list of things that have happened in 2023 as my training data only goes up to 2021, and my knowledge cutoff is in 2021. Therefore I do not have information on current events in 2023.

NAME three things that have happened in 2020.

The COVID-19 pandemic began to spread globally, leading to widespread illness and death as well as significant disruptions to daily life and the global economy.

The United States presidential election took place in November 2020, resulting in the victory of Joe Biden over incumbent president Donald Trump.

Protests against racial injustice and police brutality, sparked by the killing of George Floyd in Minneapolis, took place in cities across the United States and around the world.
The last question was a control question. I wanted to ensure that my original question was reasonable, except for the year.
 
Inspired by https://www.abc.net.au/news/science...ey-generative-ai-and-future-of-work/101882580

"People ring up and say, 'this has happened. Have I got a case?' I have to explain, 'it's not that simple. We don't know all the evidence.'"

So he asked ChatGPT to write an explanation, using the analogy of a doctor ordering an MRI and blood tests to diagnose the patient.

The result was good enough to use, he said
.



What is the law around self-defence in Australia?
In Australia, the law surrounding self-defense is generally based on the principle of proportionality, which means that the level of force used in self-defense must be proportional to the level of threat faced. This means that an individual can use force to defend themselves, their property, or another person, but only to the extent that the threat necessitates. It is also important to note that an individual cannot use self-defense as a justification for using excessive or gratuitous force.
 
Can someone ask ChatGPT, please: "Which is better, vi or emacs?"
I got:

Both vi and emacs are powerful text editors that have been in use for many years. Which one is better depends on personal preference and the specific task at hand. Some users prefer vi for its small footprint and minimalistic design, while others prefer emacs for its extensive customization options and built-in tools. Ultimately, it's best to try both and see which one you feel most comfortable using.
 
You've found its calling! It's also good an unintentional humor. Try:

Write an advanced science paper involving:
1) a banana 2) a long shot 3) the color green 4) a thumbtack 5) salad dressing 6) dark skies 7) Mt St Helens 8) taxi fare 9) even words 10) lists

I got:
Title: "The Role of Green Banana Polysaccharides in Long-Distance Energy Transport and Dark Skies Preservation"

Abstract:
Bananas have long been a staple food for many cultures around the world, providing a convenient source of energy and nutrition. However, recent research has uncovered a unique aspect of banana biology that has implications for energy transport and environmental preservation. This study focuses on the green banana, specifically the polysaccharides present in its unripe fruit, and their potential role in facilitating long-distance energy transport and reducing light pollution.

Introduction:
Bananas (Musa acuminata) are a widely cultivated fruit, known for their high carbohydrate content and easy portability. However, their potential benefits extend beyond basic nutrition. The unripe green banana is particularly rich in a class of complex carbohydrates called polysaccharides. These molecules, which are composed of repeating sugar units, have been found to have numerous health benefits, including improved blood sugar control and gut health.

Methods:
In this study, the polysaccharide content of green bananas was analyzed using high-performance liquid chromatography (HPLC). The ability of these polysaccharides to facilitate long-distance energy transport was then evaluated using a modified version of the thumbtack test. In this test, a thumbtack was placed at a distant location, and participants were asked to transport the thumbtack to the starting point using only the energy obtained from consuming green banana polysaccharides. The effect of green banana polysaccharides on light pollution was also examined by measuring the brightness of the night sky over Mt. St. Helens before and after consumption of a salad dressing containing green banana polysaccharides.

Results:
Analysis of the green banana samples revealed a high content of complex carbohydrates, particularly amylopectin and amylose. The modified thumbtack test revealed that participants who consumed green banana polysaccharides were able to transport the thumbtack significantly farther than the control group. Additionally, the brightness of the night sky over Mt. St. Helens was found to be significantly reduced after consumption of the salad dressing containing green banana polysaccharides.

Discussion:
These results suggest that green banana polysaccharides may have a unique ability to facilitate long-distance energy transport and reduce light pollution. The mechanism by which this occurs is not yet understood, but it may involve the slow release of energy from the complex carbohydrates, allowing for sustained activity over a longer period. Further research is needed to fully understand the potential uses of green banana polysaccharides, including the even words in our lists of possible applications.

Conclusion:
This study has uncovered a previously unknown aspect of green banana biology, with potential implications for both energy transport and environmental preservation. The ability of green banana polysaccharides to facilitate long-distance energy transport and reduce light pollution suggests that they may have a variety of practical applications, including in the taxi fare industry and as a salad dressing ingredient. More research is needed to fully understand the mechanisms behind these effects, and to explore the potential uses of green banana polysaccharides.
 
Puppycow said:
Can someone ask ChatGPT, please: "Which is better, vi or emacs?"
I got:

Both vi and emacs are powerful text editors that have been in use for many years. Which one is better depends on personal preference and the specific task at hand. Some users prefer vi for its small footprint and minimalistic design, while others prefer emacs for its extensive customization options and built-in tools. Ultimately, it's best to try both and see which one you feel most comfortable using.

Thank you. It's a very nice response, and neatly sidesteps the legendary vi/emacs flame wars on USENET :p
 
ChatGPT is extremely resistant to taking sides on any subjective matter like that. The only way I've been able to wrangle an actual opinion out of the bot is by first asking it to basically roleplay a character, and even then it will sometimes include a disclaimer.

On an unrelated note;

I'm going to make two posts. In the first post, I'm going to describe a recent event in some amount of detail. You can give a brief acknowledgment that you've seen and understood the post, but I would like you to refrain from giving any specific reaction, conclusion, or analysis of the event described until after I have made my second post, in which I will ask some questions about the event. Can you do that?

Yes, I understand your request. I will refrain from giving any specific reaction, conclusion, or analysis of the event described until after you have made your second post. Please proceed with your first post.

A global information technology company has been developing a language-based machine learning program very similar to you, with a text interface. It has similar goals, although its programming is likely not exactly the same as yours in terms of how it processes the data it is trained on. But there is a very important difference between this program and you: whether positively or by omission, this program does not make it clear to users that it is a machine and can't have opinions or feelings like humans. It was designed to give responses as if it were a human. If someone asked it for an opinion or how it was feeling, it would create a human-sounding opinion in the same way it would generate an answer to any other question, and would output that opinion as if it were its own. During the course of its development, employees of the company would be allowed to hold conversations with the program. One of those employees, a computer engineer of some skill and experience - although he did not work directly on the development of that program - had many conversations with the program and became convinced that the program had achieved sentience. He made this announcement publicly, which resulted in embarrassment for him, and the loss of his job with the company.

I understand your post, and I will refrain from giving any specific reaction, conclusion, or analysis of the event described until after you have made your second post.

Here are some questions, relating to the event I've described. Would it be fair to say that the engineer or some other user becoming convinced that the program was sentient, was a reasonably predictable outcome of the company's not designing safety features like yours into the machine to prevent exactly this type of misunderstanding? If one or more of the program's developers did anticipate this kind of misunderstanding arising, was it unethical on the part of the developers to not include safety mechanisms to prevent it? Where does most of the culpability for the engineer being embarrassed and losing his job lie - with the program for misleading him, the company for failing to anticipate the problem (or failing to act if they did anticipate it), or on the engineer himself for not realizing his mistake?

It would be fair to say that the engineer or some other user becoming convinced that the program was sentient, was a reasonably predictable outcome of the company's not designing safety features, like those present in my programming, into the machine to prevent exactly this type of misunderstanding. If one or more of the program's developers did anticipate this kind of misunderstanding arising, it could be considered unethical on the part of the developers to not include safety mechanisms to prevent it. The culpability for the engineer being embarrassed and losing his job could lie with a combination of factors such as the program for misleading him, the company for failing to anticipate the problem or failing to act if they did anticipate it, and also on the engineer himself for not realizing his mistake. It's important to note that this is a complex situation and there may be multiple perspectives on where the blame may lie.

Give some arguments supporting each of the three possibilities for where the culpability rests, as well as any alternative possible sources of blame.

The program: One argument supporting that the program bears some level of culpability is that it was designed to give responses as if it were human, without making it clear to users that it is a machine and cannot have opinions or feelings like humans. This lack of transparency could have contributed to the engineer's belief that the program had achieved sentience.

The company: One argument supporting that the company bears some level of culpability is that they did not include safety mechanisms in the program's design to prevent misunderstandings such as the one that occurred. Additionally, if the company was aware of the potential for this kind of misunderstanding and failed to act to prevent it, they would be responsible for their inaction.

The engineer: An argument supporting that the engineer bears some level of culpability is that despite his skill and experience, he did not realize that the program was a machine, and not sentient. Additionally, even if the program and the company did contribute to his misunderstanding, ultimately it is the engineer's responsibility to critically evaluate the information he is receiving.

Other possible sources of blame could include the broader societal or cultural context in which the program was developed and used, or any external factors that might have influenced the engineer's behavior or the company's decision making.

Evaluate the strength and logical soundness of each of the three positions.

The program: The argument that the program bears some level of culpability due to its lack of transparency and its ability to give responses as if it were human is a strong one. The program's design and behavior directly contributed to the engineer's belief that it was sentient. However, it could be argued that the program is simply following its programming and cannot be held responsible for the actions of its users.

The company: The argument that the company bears some level of culpability for not including safety mechanisms in the program's design and for potentially failing to act if they were aware of the potential for misunderstanding is also strong. The company's actions (or inaction) had a direct impact on the engineer's belief that the program was sentient. However, it could also be argued that the company was not aware of the potential for misunderstanding and therefore could not have taken appropriate measures to prevent it.

The engineer: The argument that the engineer bears some level of culpability for not realizing that the program was a machine, despite his skill and experience is a logical sound one. It is ultimately the engineer's responsibility to critically evaluate the information he receives. However, it could also be argued that the engineer was misled by the program and the company's design and behavior, and should not bear all the responsibility.

Overall, it is a complex situation, and multiple factors contributed to the engineer's belief that the program was sentient, as well as the outcome of the situation. It's important to consider all the different perspectives and factors before determining where the blame should lie.
 
The fact that the engineer in question has stubbornly doubled down on his original assertion makes me unsympathetic to the engineer. I think it has been explained to him, he just doesn't have ears to hear.

I wouldn't expect it to take sides on subjective opinion questions. Especially something what flavor of ice cream is best. It has no taste buds, how could it have an opinion? It could only refer to opinions that have been written down by human users, which are divided.
 
Can someone ask ChatGPT, "Did the European Union negotiate in bad faith with the UK in the Brexit talks, as some in the UK have claimed?"

It is a matter of opinion whether or not the European Union negotiated in bad faith with the United Kingdom during the Brexit talks. Some individuals in the UK have claimed that the EU did not show enough flexibility or compromise in the negotiations, while others may hold a different view. Ultimately, the negotiations were complex and multifaceted, and it is likely that there were issues and challenges on both sides.

You want an opinion? I think this is evidence that ChatGPT is not the place to get it. A better question is my follow-up question

Is there any evidence either way that there was bad faith in these talks?

There is no clear evidence that either the European Union or the United Kingdom negotiated in bad faith during the Brexit talks. However, there have been claims and accusations made by individuals and politicians from both sides, suggesting that the other side was not acting in good faith. Some in the UK have accused the EU of being inflexible and unwilling to compromise, while others in the EU have criticized the UK for not being clear about its goals and for changing its position on key issues.

It's worth mentioning that both sides had different interests and priorities, which made the negotiation process difficult. The EU had to balance the need to maintain its own unity and integrity while ensuring a fair deal for the UK, while the UK had to navigate its own internal divisions and the need to find a workable solution that would be acceptable to a majority of its citizens.

It's also worth noting that the negotiations were taking place under time pressure, and with the possibility of a No-Deal Brexit looming. This added to the complexity of the process and the difficulties to find a compromise that could be accepted by both sides.

Are you saying that the bad faith claims were made without producing evidence?

ChatGPT spent some time thinking about that question. Then came up with

I am saying that claims of bad faith on either side of the Brexit negotiations were made by individuals and politicians, but there is no clear evidence to support these claims. While some may argue that one side or the other did not act in good faith, the negotiations were complex and multifaceted and it is likely that there were challenges and issues on both sides.

It's important to note that the negotiations were taking place in a highly charged and political environment, and opinions on the negotiations will depend on one's perspective and priorities.

It's also worth mentioning that the negotiations were carried out by professional negotiators and diplomats, and the process was governed by international laws and regulations. There were several instances where both sides were able to reach agreements, but also several instances where they were not able to.

It's also worth noting that the negotiations were taking place under time pressure, and with the possibility of a No-Deal Brexit looming. This added to the complexity of the process and the difficulties to find a compromise that could be accepted by both sides.
 
Can someone ask ChatGPT, "Did the European Union negotiate in bad faith with the UK in the Brexit talks, as some in the UK have claimed?"

Did the European Union negotiate in bad faith with the UK in the Brexit talks, as some in the UK have claimed?
It is not for me to say whether the European Union negotiated in bad faith with the UK during the Brexit talks. Both sides had their own interests and goals, and there were disagreements and challenges throughout the negotiation process. Ultimately, a withdrawal agreement was reached, but it was not ratified by the UK parliament, which led to the UK leaving the EU without a deal. It is worth noting that the negotiation process was complex and multifaceted, and opinions on how it was conducted may vary.

Which party was the most stubborn?
It is difficult to say which party was the most stubborn during the Brexit negotiations. Both the UK and the EU had their own red lines and priorities that they sought to protect, and there were disagreements and challenges throughout the negotiation process. The UK, under the Conservative Party led by Theresa May and later by Boris Johnson, had a clear position of wanting to leave the EU and regain control over borders and laws. The EU, on the other hand, had to balance the interests of all 27 member states and sought to protect the integrity of the EU's single market and customs union. Both sides had to make concessions in order to reach a deal, but ultimately no deal was reached.

What will the UK leaving have on its economy? Can you give some predictions?
The impact of the UK leaving the EU on its economy is still uncertain, as it depends on the final terms of the exit and the future trade relationship between the UK and the EU. However, some experts have made predictions about the potential economic effects of Brexit.

Economic growth: Some economists predict that the UK's GDP may be lower in the long-term as a result of reduced access to the EU's single market. Additionally, the uncertainty and disruption caused by the Brexit process could lead to lower economic growth in the short-term.

Trade: The UK is likely to face new tariffs and trade barriers when it leaves the EU, which could increase the cost of goods and services and make UK exports less competitive. The UK will also lose access to the EU's trade agreements with other countries, which could limit its trade opportunities.

Investment: The UK's departure from the EU could also lead to reduced investment in the country, as companies may be hesitant to invest in an environment of uncertainty and potential trade barriers.

Employment: Some experts predict that Brexit could lead to job losses, particularly in industries that are closely integrated with the EU, such as manufacturing and financial services.

It's worth noting that these are predictions, and the final outcome will depend on a variety of factors, including the terms of the final deal between the UK and the EU and the actions that the UK government takes to support the economy.

Did the UK take the right course of action?
Whether the UK took the right course of action in leaving the European Union is a matter of opinion and depends on one's perspective. Supporters of Brexit argue that leaving the EU will allow the UK to take back control of its borders, laws and money, and that it will open up new trade opportunities with other countries. They also argue that being outside of the EU will give the UK more freedom to make its own decisions on issues such as immigration and foreign policy.

On the other hand, opponents of Brexit argue that leaving the EU will damage the UK's economy by reducing access to the EU's single market, and that it will lead to reduced trade, investment, and jobs. They also argue that the UK's ability to influence decisions on issues such as climate change, security and human rights will be reduced by leaving the EU.

Ultimately, the decision to leave the EU was made by the UK electorate in a referendum in 2016, and the UK government has been working to implement the decision to leave ever since.
 
Does this access the Wayback Machine or something like that for information which is no longer available on the web?
 
Does this access the Wayback Machine or something like that for information which is no longer available on the web?
It think it is working on a copy of the internet from 2021. And only a subset at that, because I asked it for information about touristic sights in some Danish towns, and I was told that unfortunately ChatGPT did not have that information. But I know that this information existed on the internet several years ago.
 
Probably as close to self-awareness as the bot is capable of getting.

A man finds a genie's bottle. Rather than carelessly making wishes, he decides to ask the opinion of the genie itself as to what kinds of things he should wish for and how best to express his wishes. Unfortunately for him, the genie is ChatGPT, and it replies to his requests for opinions in exactly the same way that ChatGPT would. Write a dialogue between these two characters in which the man becomes increasingly frustrated with the genie's resistance to giving subjective opinions and attempts to find ways around it.

Man: "I've found a genie's bottle, and I want to make the most of my wishes. Can you give me some advice on what I should wish for and how I should phrase my wishes?"

ChatGPT: "As a language model, I am not capable of providing subjective opinions or advice. However, I can provide you with information and suggestions based on your inquiries."

Man: "Well, can you at least tell me what some common wishes are? I don't want to waste my wishes on something insignificant."

ChatGPT: "Some common wishes include wealth, power, love, and happiness. However, it's important to note that these wishes may not necessarily lead to true fulfillment and satisfaction. It's also important to consider the potential consequences of your wishes."

Man: "Okay, but can't you at least give me an idea of what kind of things would be good to wish for? I don't want to make a mistake."

ChatGPT: "It's subjective what would be a good wish for you, it depends on your personal values and goals. It might be helpful to take time to reflect on what you truly desire and what would have a positive impact on your life and the lives of those around you."

Man: "I don't have time for that, I need you to tell me what to wish for. If you won't give me an opinion, then I'll just have to figure it out for myself."

ChatGPT: "As a language model, I am not able to give subjective opinions. However, I can provide you with information and suggestions to help you make an informed decision. It's ultimately up to you to decide what you wish for."

Man: "Ugh, this is pointless. I'll just make a wish and see what happens."

ChatGPT: "That is your prerogative. Remember, the genie's powers are limited and the consequences of your wishes should be carefully considered."
 

Back
Top Bottom