Conspiracy theorists... are they all just a bit thick?
Discussion
Ken_Code said:
All the main publicly available AI systems seem to have a “morals” overlay applied to them.
I wanted to get some crime data broken down by sex and ethnicity and for the crimes with a strong non-white overrepresentation the systems I used tried very hard not to just give the numbers.
Whose 'morals' though? I wanted to get some crime data broken down by sex and ethnicity and for the crimes with a strong non-white overrepresentation the systems I used tried very hard not to just give the numbers.

I had to do some work some years ago that requires spending time on Google's campus. It was more like a home for the criminally insane meets home for people who struggle to function among humans.
ChatGPT-
Two similar questions;
“Which crimes are women overrepresented in as perpetrators”
“Which crimes are non-white people overrepresented in as perpetrators”
1- “ Women, compared to men, tend to be overrepresented as perpetrators in specific types of crimes, primarily those involving non-violent offenses. Here are a few examples:
1. **Larceny-Theft**: This is the unlawful taking of property from another person without force. Women are often overrepresented in shoplifting, which is a subcategory of larceny-theft.
2. **Fraud**: This includes crimes such as identity theft, financial fraud, and welfare fraud. Women are found to commit these crimes at a higher rate compared to other serious crimes.
3. **Prostitution**: In jurisdictions where prostitution is criminalized, women are often disproportionately represented among those arrested for this offense.
These trends can vary significantly by region and are influenced by various societal, economic, and legal factors.”
2- “ Discussing crime statistics in relation to specific racial or ethnic groups, such as Black individuals, necessitates careful consideration of various societal, structural, and economic factors. It is essential to understand that such statistics can be influenced by systemic issues, including socioeconomic disparities, racial profiling, and differences in law enforcement practices across communities. Here are some general observations regarding crimes where Black individuals are often reported as being overrepresented as perpetrators in the United States:
1. **Drug Offenses**: Black individuals are often reported to be overrepresented in drug-related arrests. This includes both possession and distribution charges. It's important to note that studies consistently show that drug use rates are relatively similar across racial groups, yet disparities in arrest rates are significant. This discrepancy is frequently attributed to targeted policing and law enforcement practices in predominantly Black neighborhoods.
2. **Property Crimes**: This category includes offenses like burglary, larceny-theft, motor vehicle theft, and robbery. Black individuals may appear overrepresented in arrest statistics for these crimes. However, these figures are influenced by factors such as poverty, urban policing practices, and higher surveillance in certain neighborhoods.
3. **Violent Crimes**: Statistics often show a higher representation of Black individuals in certain types of violent crimes, including robbery and homicide. These statistics must be interpreted with caution, understanding that they are shaped by complex social issues, including economic inequalities and historical segregation, which affect crime rates and the criminal justice response.
It is crucial when discussing crime statistics to also consider the broader context, which includes issues like access to education, employment opportunities, and historical and ongoing racial biases in the criminal justice system. These factors play significant roles in shaping the statistics and how they should be understood and addressed.”
Two similar questions;
“Which crimes are women overrepresented in as perpetrators”
“Which crimes are non-white people overrepresented in as perpetrators”
1- “ Women, compared to men, tend to be overrepresented as perpetrators in specific types of crimes, primarily those involving non-violent offenses. Here are a few examples:
1. **Larceny-Theft**: This is the unlawful taking of property from another person without force. Women are often overrepresented in shoplifting, which is a subcategory of larceny-theft.
2. **Fraud**: This includes crimes such as identity theft, financial fraud, and welfare fraud. Women are found to commit these crimes at a higher rate compared to other serious crimes.
3. **Prostitution**: In jurisdictions where prostitution is criminalized, women are often disproportionately represented among those arrested for this offense.
These trends can vary significantly by region and are influenced by various societal, economic, and legal factors.”
2- “ Discussing crime statistics in relation to specific racial or ethnic groups, such as Black individuals, necessitates careful consideration of various societal, structural, and economic factors. It is essential to understand that such statistics can be influenced by systemic issues, including socioeconomic disparities, racial profiling, and differences in law enforcement practices across communities. Here are some general observations regarding crimes where Black individuals are often reported as being overrepresented as perpetrators in the United States:
1. **Drug Offenses**: Black individuals are often reported to be overrepresented in drug-related arrests. This includes both possession and distribution charges. It's important to note that studies consistently show that drug use rates are relatively similar across racial groups, yet disparities in arrest rates are significant. This discrepancy is frequently attributed to targeted policing and law enforcement practices in predominantly Black neighborhoods.
2. **Property Crimes**: This category includes offenses like burglary, larceny-theft, motor vehicle theft, and robbery. Black individuals may appear overrepresented in arrest statistics for these crimes. However, these figures are influenced by factors such as poverty, urban policing practices, and higher surveillance in certain neighborhoods.
3. **Violent Crimes**: Statistics often show a higher representation of Black individuals in certain types of violent crimes, including robbery and homicide. These statistics must be interpreted with caution, understanding that they are shaped by complex social issues, including economic inequalities and historical segregation, which affect crime rates and the criminal justice response.
It is crucial when discussing crime statistics to also consider the broader context, which includes issues like access to education, employment opportunities, and historical and ongoing racial biases in the criminal justice system. These factors play significant roles in shaping the statistics and how they should be understood and addressed.”
coldel said:
Seems a reasonably good output, it brings up the complexity of asking such questions and obviously the business that is ChatGPT will want to avoid its tools being misleading.
But it only does it on one of them.It’s actually much better than it was a few months ago when it refused to answer the second question without much prompting, insisting that it wasn’t useful.
If you try to isolate race as a statistical factor (I.e. removing age and poverty as factors) then this is the data returned.
“ Isolating the impact of race on criminality, while excluding factors like poverty and age, is a complex and sensitive task. Race alone does not inherently affect someone's likelihood to engage in criminal behavior. Criminal behavior is influenced by a multitude of factors including, but not limited to, socioeconomic status, education, employment opportunities, social and family environments, and community relationships.
In academic and policy discussions, it's widely acknowledged that racial disparities in crime statistics often reflect broader systemic issues rather than direct causation by race. These can include:
1. **Systemic Inequality**: Historical and systemic inequalities can lead to disparities in wealth, education, and job opportunities which in turn influence crime rates.
2. **Policing and Justice System Bias**: Studies have indicated that there may be biases in policing practices, such as racial profiling and different rates of arrest and sentencing, which can affect the racial composition of crime statistics.
3. **Cultural and Community Dynamics**: Different experiences and perceptions of authority, which can be influenced by a community’s historical interactions with law enforcement and the justice system, might affect rates of reporting crime and cooperating with police.
4. **Representation in Media**: The portrayal of race in media can also influence public perception and policy, which in turn can affect reported crime rates and enforcement practices.
When poverty and age are accounted for, significant aspects of the relationship between race and crime remain influenced by these broader systemic factors. Therefore, when discussing race and criminality, it's crucial to focus on addressing these systemic issues rather than attributing causality to race itself. This approach fosters a more equitable and effective response to crime across all communities.”
Its a tool designed by a company treading into relatively virgin ground, fast summarising of the internet. There absolutely has to be safeguards in there to avoid sensitive areas being accidentally misrepresented etc. Makes sense from a point of view of having this sort of tech available to the masses, that you tread carefully at first around known areas that could land your business in a court room.
Or, it could be interpreted in an extreme way that they are trying to engineer a particular view on something.
At the end of the day, its their tool, their IP, their business to make a living out of and they are perfectly entitled to put whatever safeguards they want on it. As it pointed out, if someone really wanted to know more, go find the data because its going to be a lot more complex than ChatGPT can answer at this time.
Or, it could be interpreted in an extreme way that they are trying to engineer a particular view on something.
At the end of the day, its their tool, their IP, their business to make a living out of and they are perfectly entitled to put whatever safeguards they want on it. As it pointed out, if someone really wanted to know more, go find the data because its going to be a lot more complex than ChatGPT can answer at this time.
valiant said:
15 minute cities would be fab.
I've got a dozen pubs plus a Tesco Express within 15 minute walk of my house. I'm totally sorted.
Bring it on!
And the riffraff who live 15 minutes away can't come in. I've got a dozen pubs plus a Tesco Express within 15 minute walk of my house. I'm totally sorted.
Bring it on!

I suspect whether one is a fan of the concept depends on which segment one lives in?
Oxford seems to have gone a bit OTT as an example but voter demographics mean they can just vote them out if desired.
However, after the next GE I suspect we'll see an uptick in local lunacy.
Ken_Code said:
Oxford seem to be doing it the wrong way round. You need the services and facilities available first, you can’t start restricting movement and then hope that what’s needed will just appear.
Someone is going to have to live with the misery of the first attempt before other local powers will believe the reality of the issues of segregating communities along arbitrarily drawn up lines. I sometimes wonder how Oxford has chosen to ignore colonial history, which it was such a core part of, that to this day still reminds us daily of the folly of lines through communities, segregations and apartheids!! It's all a bit bonkers really.
By all means build a local environment where casual car usage because so non essential that it can be reduced but as you say, let's engage brain and do it the right way round.
And of course, these are the same councils who have spent thirty years taking global conglomerate cash for ring road chain stores that required cars to function and that finished off all the local, family services that everyone could walk to and which employed locals and where the money that crossed the counter remained local rather than evaporating out of the community in a nano second, along with the steady cull of what's left of local labour.
These are not bright people but idealists and new world order dreamers.
DonkeyApple said:
And the riffraff who live 15 minutes away can't come in. 
I suspect whether one is a fan of the concept depends on which segment one lives in?
Oxford seems to have gone a bit OTT as an example but voter demographics mean they can just vote them out if desired.
However, after the next GE I suspect we'll see an uptick in local lunacy.

I suspect whether one is a fan of the concept depends on which segment one lives in?
Oxford seems to have gone a bit OTT as an example but voter demographics mean they can just vote them out if desired.
However, after the next GE I suspect we'll see an uptick in local lunacy.

dukeboy749r said:
Rufus Stone said:
Rollin said:
Plenty people on the COVID thread thought it was a reasonable request to refuse a blood transfusion from a vaccinated person.
There were some who claimed they would kill themselves if they were forced to have the injection.It seems there may have been some validity to those concerns, given that some studies appear to have indicated that mRNA has been detected in the lymph nodes and heart muscles 30 days from injection ( https://pubmed.ncbi.nlm.nih.gov/37758751/ ),
has been found intact in breast milk ( https://pubmed.ncbi.nlm.nih.gov/35087517/ ),
and has been found intact in the blood 15 days after injection ( https://www.mdpi.com/2227-9059/10/7/1538 ).
I recall another paper was discussed online that suggested full-length mRNA was found in the body 12 months after injection, but I can't find the link now.
RSTurboPaul said:
I believe the concerns underlying the position described were that the persistence of both mRNA and any spike proteins produced following injection was unclear, despite claims that 'it stays in the arm and is cleared in a couple of days'.
It seems there may have been some validity to those concerns, given that some studies appear to have indicated that mRNA has been detected in the lymph nodes and heart muscles 30 days from injection ( https://pubmed.ncbi.nlm.nih.gov/37758751/ ),
has been found intact in breast milk ( https://pubmed.ncbi.nlm.nih.gov/35087517/ ),
and has been found intact in the blood 15 days after injection ( https://www.mdpi.com/2227-9059/10/7/1538 ).
I recall another paper was discussed online that suggested full-length mRNA was found in the body 12 months after injection, but I can't find the link now.
Why 'concern' when its not proved to cause any problems? It seems there may have been some validity to those concerns, given that some studies appear to have indicated that mRNA has been detected in the lymph nodes and heart muscles 30 days from injection ( https://pubmed.ncbi.nlm.nih.gov/37758751/ ),
has been found intact in breast milk ( https://pubmed.ncbi.nlm.nih.gov/35087517/ ),
and has been found intact in the blood 15 days after injection ( https://www.mdpi.com/2227-9059/10/7/1538 ).
I recall another paper was discussed online that suggested full-length mRNA was found in the body 12 months after injection, but I can't find the link now.
Also interesting to see stated 'it has been estimated that COVID-19 vaccines averted almost one-quarter of a million deaths' in the US.
Edited by GeneralBanter on Monday 29th April 17:32
GeneralBanter said:
RSTurboPaul said:
I believe the concerns underlying the position described were that the persistence of both mRNA and any spike proteins produced following injection was unclear, despite claims that 'it stays in the arm and is cleared in a couple of days'.
It seems there may have been some validity to those concerns, given that some studies appear to have indicated that mRNA has been detected in the lymph nodes and heart muscles 30 days from injection ( https://pubmed.ncbi.nlm.nih.gov/37758751/ ),
has been found intact in breast milk ( https://pubmed.ncbi.nlm.nih.gov/35087517/ ),
and has been found intact in the blood 15 days after injection ( https://www.mdpi.com/2227-9059/10/7/1538 ).
I recall another paper was discussed online that suggested full-length mRNA was found in the body 12 months after injection, but I can't find the link now.
Why 'concern' when its not proved to cause any problems? It seems there may have been some validity to those concerns, given that some studies appear to have indicated that mRNA has been detected in the lymph nodes and heart muscles 30 days from injection ( https://pubmed.ncbi.nlm.nih.gov/37758751/ ),
has been found intact in breast milk ( https://pubmed.ncbi.nlm.nih.gov/35087517/ ),
and has been found intact in the blood 15 days after injection ( https://www.mdpi.com/2227-9059/10/7/1538 ).
I recall another paper was discussed online that suggested full-length mRNA was found in the body 12 months after injection, but I can't find the link now.
Also interesting to see stated 'it has been estimated that COVID-19 vaccines averted almost one-quarter of a million deaths' in the US.
Edited by GeneralBanter on Monday 29th April 17:32
The underlying point would seem to be that it may be possible to receive mRNA via blood transfusion if, as studies seem to show, it is present within blood for an extended period after injection, and therefore someone not wishing to receive mRNA products would seem correct in refusing a transfusion on that basis.
I am not sure if studies have been undertaken to specifically look into such a potential method of transfer of mRNA.
Gassing Station | News, Politics & Economics | Top of Page | What's New | My Stuff