ChatGPT - Church FISA < Patriot FISA
The rise of the machines...
Seems like ChatGPT has been getting a lot of press lately, both good and bad. So, I thought I’d check it out. I went off the theme of Friday’s substack and issued it a few prompts as distinguished with block quotes. I also added some additional commentary as distinguished in bold and italicized font. Let me know what you think about what was generated as well as what you think of ChatGPT in the comments! For additional AI technology, if you have the Substack App (available for Android and Apple) you can listen to an AI voice read the substack.
—GOB
Preface: What is ChatGPT? According to Wikipedia (hopefully readers aren’t still stuck in the early 2000’s belief that Wikipedia is not reliable…of course it is up to us to “fact check” everything ourselves, however their chatGPT page is well cited and seems reliable on it’s face), “ChatGPT (Chat Generative Pre-trained Transformer) is a chatbot launched by OpenAI in November 2022. It is built on top of OpenAI's GPT-3 family of large language models, and is fine-tuned (an approach to transfer learning) with both supervised and reinforcement learning techniques.
“ChatGPT was launched as a prototype on November 30, 2022, and quickly garnered attention for its detailed responses and articulate answers across many domains of knowledge. Its uneven factual accuracy was identified as a significant drawback. Following the release of ChatGPT, OpenAI was valued at $29 billion.
“Although the core function of a chatbot is to mimic a human conversationalist, ChatGPT is versatile. For example, it has the ability to write and debug computer programs; to compose music, teleplays, fairy tales, and student essays; to answer test questions (sometimes, depending on the test, at a level above the average human test-taker); to write poetry and song lyrics; to emulate a Linux system; to simulate an entire chat room; to play games like tic-tac-toe; and to simulate an ATM. ChatGPT's training data includes man pages and information about Internet phenomena and programming languages, such as bulletin board systems and the Python programming language.”
In the below video, Joe Rogan and Bret Weinstein discuss ChatGPT. Weinstein talks about some of the potential dangers associated with ChatGPT.
What can you tell me about the Patriot Act?
The USA PATRIOT Act (Uniting and Strengthening America by Providing Appropriate Tools Required to Intercept and Obstruct Terrorism Act) is a law passed by the U.S. Congress in 2001 in response to the 9/11 terrorist attacks. It grants law enforcement agencies increased surveillance and investigative powers, including the ability to search a person's home or business without their knowledge or consent, and to gather intelligence on individuals and organizations without a traditional warrant. The Act also expands the government's ability to share information between agencies, and makes it easier for law enforcement to track financial transactions and Internet activity. The law was reauthorized in 2006 and again in 2011, and some provisions of the Act have been the subject of controversy and legal challenges.
What controversy and legal challenges has the USA PATRIOT Act been subjected to?
The USA PATRIOT Act has been the subject of controversy and legal challenges since its passage in 2001, primarily due to concerns over civil liberties and privacy. Critics argue that the Act grants law enforcement agencies too much authority to conduct surveillance and investigations without proper oversight, and that some of its provisions, such as the ability to search a person's home or business without their knowledge or consent, and to gather intelligence on individuals and organizations without a traditional warrant, are too broad and open to abuse.
One of the most controversial provisions of the Act is Section 215, which allows the government to obtain "any tangible things" relevant to a terrorism investigation with a secret court order. This provision has been used to justify the bulk collection of phone metadata, which was revealed by Edward Snowden's leaks in 2013. This revelation led to the USA Freedom Act in 2015, which ended the bulk collection of phone data.
(Author’s note: I’ll take some exception with what was generated here. The government has claimed that bulk collection of phone data has ended. But has it really? The NSA still has that capability. It would be foolish to think they destroyed it or keep locked away somewhere. Also, that capability should be used against foreign adversaries. But, as discussed over the last handful of substacks, the government has a decades and decades long track record of consistently using their power against their own citizens. Furthermore, along with TITANPOINTE there are seven other similar hubs around the country. Again I’ll ask, has the bulk collection truly ended? All of that information is classified and Edward Snowden’s leaks are a decade old. What other nefarious activity has the government been keeping hidden since then? If anything, they’ve likely further compartmentalized these types of programs to keep them hidden from the public. Back to the AI.)
The Act has also been challenged in court on constitutional grounds, with some arguing that it violates the Fourth Amendment's protection against unreasonable searches and seizures. However, the Supreme Court of the United States has not yet ruled on the constitutionality of the USA PATRIOT Act.
Additionally, the PATRIOT Act's provisions related to surveillance and the collection of data has been a concern for privacy advocates, who see it as a violation of individual's right to privacy and freedom of speech.
What else can you tell me about Section 215 of the USA PATRIOT Act?
Section 215 of the USA PATRIOT Act, also known as the "business records provision," allows the government to obtain "any tangible things" relevant to a terrorism investigation with a secret court order. This provision has been interpreted by the government to include the bulk collection of phone metadata, which includes information such as phone numbers, call durations, and call locations, but not the content of the calls. This practice was revealed by Edward Snowden's leaks in 2013, which led to widespread public concern over privacy and civil liberties.
The provision also allows the government to obtain library records, medical records, and other sensitive personal information in the course of a terrorism investigation. Critics argue that the provision is too broad and open to abuse, and that the secret court process used to approve these requests does not provide sufficient oversight or due process.
In 2015, the USA Freedom Act was passed, which ended the bulk collection of phone data under Section 215, and established new guidelines for the collection and retention of phone metadata. The Act also increased transparency by requiring the government to disclose certain information about its use of Section 215, and created a panel of privacy advocates to argue against government requests in front of the Foreign Intelligence Surveillance Court.
However, Section 215 is still in effect, and the government can still use it to request any tangible thing that is relevant to a terrorism investigation, with an approval from the Foreign Intelligence Surveillance Court (FISC) and with certain guidelines and restrictions.
What does the FISC do?
The Foreign Intelligence Surveillance Court (FISC) is a special court established by the Foreign Intelligence Surveillance Act (FISA) of 1978. It is responsible for issuing and overseeing orders for electronic surveillance and physical searches for foreign intelligence purposes. The court operates in secrecy and its proceedings are not open to the public.
The FISC is composed of eleven federal district court judges who are appointed by the Chief Justice of the United States. They are responsible for reviewing and approving requests for surveillance and search warrants submitted by the government, primarily the Federal Bureau of Investigation (FBI) and the National Security Agency (NSA), for foreign intelligence and counterintelligence purposes. The court also oversees compliance with the rules and procedures established by FISA and the USA PATRIOT Act, and has the authority to modify or revoke an order if it finds that the government has not met the required standards.
The FISC has been criticized for being too secretive and not providing enough oversight, and some have argued that the court rubber stamps the government's requests and has not served as an effective check on government surveillance powers. However, the court has rejected some government requests in the past, and the government must provide a probable cause based on the facts and evidence that are presented to the court.
(Author’s note: I’ll again take exception here. We know that the government denied only .03% of FISA’s, approving 99.97%. For anyone, even an AI to state “the court has rejected some government requests in the past” is deceptive at best. Sure, it has rejected some. 11 out of over 33,000 when that information came out. Also, of those 11, how many of them were redrafted and then approved? We don’t know because YOUR “national security” is kept as a secret from YOU. Back to the AI.)
In light of the controversy around the government's use of surveillance powers under the USA PATRIOT Act, some have called for more transparency and oversight of the FISC's operations, including the release of its opinions to the public.
What can you tell me about FISA abuse by the FBI and NSA?
There have been allegations of abuse of the Foreign Intelligence Surveillance Act (FISA) by the Federal Bureau of Investigation (FBI) and the National Security Agency (NSA) in the past. These allegations generally revolve around the idea that the agencies have used the broad powers granted to them by FISA and the USA PATRIOT Act to conduct surveillance on American citizens without sufficient oversight or probable cause.
One of the most high-profile examples of alleged FISA abuse was revealed by Edward Snowden's leaks in 2013. Snowden, a former contractor for the NSA, leaked classified documents that revealed the extent of the government's surveillance programs, including the bulk collection of phone metadata under Section 215 of the USA PATRIOT Act. This revelation led to widespread public concern over privacy and civil liberties, and led to the passage of the USA Freedom Act in 2015, which ended the bulk collection of phone data under Section 215.
(Author’s note: The government and media portrayed Snowden as a traitor back then. Most still do. Why is that? The claim often is because he revealed “national security secrets.” Ok, fine. Claim that all you want. Even if that is true, which is highly debatable, why was the government keeping those secrets? The government collecting bulk metadata on Americans has nothing to do with “national security.” It has everything to do with government overreach. Yet, Snowden is still wanted by the government and maligned as a traitor. Sadly, I bought that narrative back then. Now, I think at least, I approach these types of topics with more nuance and thought than I once did. Back to the AI.)
Another example is the Inspector General report of 2019 that found that the FBI had made several errors and omissions in its applications for surveillance warrants under FISA for investigation into the Trump campaign. The report also found that the FBI had not adequately documented the justification for their request, and that the mistakes made on the applications were serious and widespread.
(Author’s note: That’s all we get? One small paragraph? I barely gave the reader’s digest version of these events in the last post. This is sad and reminiscent of a mainstream outlet’s “reporting.” Remember, FISA, FISC, FBI counterintelligence, etc. are all SECRET. The only reason anyone ever found out about this is because Trump ended up being elected, even with all the government interference leading up to the election, including the numerous abuses by the FBI. We likely only found out about this because Trump and those in his Cabinet and on his staff had the requisite need to know and clearances to learn that this occurred. How many other FISA’s have you ever heard of before? Probably not many because the government does all they can to keep them secret from you. Most of them probably should remain secret, at least for the duration of the investigation, if they are concerning actual foreign intelligence or counterintelligence. But since they almost never get revealed, they are used abusively, as the one primary example we have to go off of has shown. Back to the AI.)
It's important to note that the vast majority of the FISA applications are approved by the FISC, and the court has rejected some government requests in the past. The oversight process is in place to ensure the legality and constitutionality of the surveillance activities. However, any abuse of the FISA process by any government agency, if proven, would be a serious violation of civil liberties and privacy rights of citizens.
Is there anything else I should know about government abuse regarding FISA and the Patriot Act?
There have been several other instances of government abuse and overreach related to FISA and the PATRIOT Act. One example is the use of National Security Letters (NSLs), which are issued by the FBI and allow the agency to obtain certain types of personal information about individuals without a court order. The PATRIOT Act expanded the scope of NSLs and made it easier for the FBI to obtain them. However, a number of abuses of this power have been reported, including the use of NSLs to obtain information about individuals who were not connected to a terrorism or espionage investigation.
Another example is the use of "Sneak and Peek" warrants, which allow law enforcement to conduct searches of private property without immediately informing the person whose property is being searched. These warrants were also expanded by the PATRIOT Act, and have been criticized for being used in non-terrorism related investigations and for violating the Fourth Amendment's protection against unreasonable searches and seizures.
Additionally, there have been concerns about the lack of transparency and accountability surrounding the use of these laws. For example, the FISC operates in secret and its proceedings and decisions are not available to the public. This lack of transparency makes it difficult for citizens to know how the government is using these powers and whether they are being used in accordance with the law.
It's also worth mentioning that the PATRIOT Act and FISA have been the subject of legal challenges and court cases, some of which have resulted in changes to the law or the way it is implemented.
In conclusion, while the PATRIOT Act and FISA were passed with the intention of protecting the nation from terrorism, there have been a number of reported instances of government abuse and overreach related to these laws. These include the use of National Security Letters and "Sneak and Peek" warrants in non-terrorism related investigations, as well as concerns about the lack of transparency and accountability surrounding their use. Civil rights activists and other critics of these laws argue that they have resulted in serious violations of civil liberties and privacy rights and that they need to be reformed to ensure that they are not open to abuse and that they provide sufficient oversight and due process.
—
That is where I ended since the generated text was about as long as what I wrote. It took me less than ten minutes. What an interesting time to be alive. Hopefully, you still think what I, as a human, put together is a bit more intriguing. Let me know in the comments what you thought of this exercise!
A couple short/intermediate problems I see with not only ChatGPT but “AI” (the definition as used in applications today is pretty broad) in general is (1) built in bias and (2) unintended consequences in human development, or more accurately lack of human development.
Every single human being has biases... we all have a world view shaped by beliefs, experiences, etc. ChatGPT has been created by humans, with not only their language models/algorithms as defined in the code written by these humans, but also content policy intended to be guardrails. Inevitable, those guardrails (which have already been tricked) are going to be determined in part by the creators built in biases. So, this creates, intentional or not, a new path to pass these biases through something that’s “non-human” which in turn presents the opportunity for people to not filter it the same way as they might from another human. Potentially disruptive to say the least, and that doesn’t begin to explore more sinister uses for it.
Secondly, what happens as this tech improves? While you were able to point out some faults with its response, how many others that aren’t as familiar with the subject would be able to? How confident are we that it’s use can be limited to appropriate use cases? What’s to prevent students from employing it to write every single paper they need to? Are we providing the means to short circuit one’s own intellectual development and learning process by providing a tool like this? I don’t know the answer, but I don’t think it’s completely benign in this regard.
The longer term/more theoretical issue is what Rogan and Weinstein discussed. I would argue the true goal of “AI” is to create something smarter than humans. And Weinstein is exactly right... if it’s possible to achieve, how do we know when this intelligence gets to that point? And the bigger question, why should we expect to control it at that point? If you can create something capable of solving problems that humans can’t, it’s also capable of creating problems humans can’t solve. And that’s the real issue, once again it’s human hubris.