Pages

Friday, December 23, 2022

AI chatbots are a potential danger for fact-based Israel advocacy



The New York Times reported:

Over the past three decades, a handful of products like Netscape’s web browser, Google’s search engine and Apple’s iPhone have truly upended the tech industry and made what came before them look like lumbering dinosaurs.

Three weeks ago, an experimental chat bot called ChatGPT made its case to be the industry’s next big disrupter. It can serve up information in clear, simple sentences, rather than just a list of internet links. It can explain concepts in ways people can easily understand. It can even generate ideas from scratch, including business strategies, Christmas gift suggestions, blog topics and vacation plans.

Although ChatGPT still has plenty of room for improvement, its release led Google’s management to declare a “code red.” For Google, this was akin to pulling the fire alarm. Some fear the company may be approaching a moment that the biggest Silicon Valley outfits dread — the arrival of an enormous technological change that could upend the business.

For more than 20 years, the Google search engine has served as the world’s primary gateway to the internet. But with a new kind of chat bot technology poised to reinvent or even replace traditional search engines, Google could face the first serious threat to its main search business. One Google executive described the efforts as make or break for Google’s future.
Imagine a future where you ask a question to a website and you get a well-formatted, professional looking answer - and it is all wrong.

ChatGPT is an amazing technology, but it bases its answers on, well, no one is really sure. I asked it to write a blog post about torture in Palestinian jails, and it mentioned a couple of specific examples of people tortured to death - and they were both completely wrong. But there was no link to where it got its information from, and it all sounded authoritative. 

This problem already exists to some extent even in popular search engines. Google and others will try to put a summary of the answer they think you want on top of the search page results, often but not always citing Wikipedia, which has its own issues with reliability.

But if AI replaces search, people will implicitly trust what they read as if it is engraved in stone. 

Give that AI typically takes its knowledge from the Internet, and that antisemites outnumber Jews by far online, the chances that an AI chatbot answering questions about Israel accurately are not too high. 

I asked, "After the UN partition vote in 1947, which side attacked the other first?"

ChatGPT gave a generic "both sides" answer: "After the United Nations voted in favor of the partition of Palestine in 1947, tensions between Jewish and Palestinian communities in the region escalated, eventually leading to the outbreak of violence and armed conflict. There were attacks by both sides, with Palestinian Arab militants and Jewish militant groups engaging in acts of violence and terrorism against one another. The conflict eventually escalated into full-scale war in 1948, with the newly formed state of Israel being invaded by several Arab countries. The war ended in 1949 with a series of armistice agreements, but the conflict between Israelis and Palestinians continued to flare up periodically in the ensuing decades."

It isn't exactly lying, but it didn't tell the truth either, that Arabs attacked Jews within hours of the vote.

When I asked, "Who are the most notorious terrorists in the Arab/Israeli conflict?", it answered:

Terrorism has been a significant factor in the Arab-Israeli conflict, with various groups and individuals on both sides of the conflict carrying out acts of terrorism against the other side. Some of the most well-known terrorists in the conflict include:

Yasser Arafat: Palestinian leader and founder of the Palestine Liberation Organization (PLO), which was involved in numerous acts of terrorism against Israel.

Menachem Begin: Israeli politician and former Prime Minister of Israel, who was a member of the Irgun, a Jewish militant group that carried out numerous acts of terrorism against the British and Arabs during the 1940s.

Ahmed Yassin: Palestinian cleric and co-founder of Hamas, a Palestinian Islamist organization that has carried out numerous suicide bombings and other terrorist attacks against Israel.

Shimon Peres: Israeli politician and former Prime Minister of Israel, who was involved in the Stern Gang, a Jewish militant group that carried out numerous acts of terrorism against the British during the 1940s.

Abu Nidal: Palestinian militant and founder of the Abu Nidal Organization, which carried out numerous terrorist attacks against Israel and other Western countries.

It is important to note that terrorism is a highly controversial and inflammatory term, and different people may have different definitions of what constitutes terrorism. It is also important to recognize that the actions of individual terrorists do not represent the views or beliefs of all members of the group or community to which they belong.
This is again an attempt to "both sides" the question. Even worse, Shimon Peres was never a member of the Stern Gang. Where did it get that from?  We have no idea. And the last paragraph seems meant to blunt the idea of Hamas and Fatah as still promoting terror, even though they do, today.

There is a mindset, so to speak, that makes the AIs so seemingly human-like - but as we see, it ultimately reflects the thinking of the programmers as well as the data set that is chosen to be authoritative. Real objectivity is impossible, so naturally we will be seeing opinions that align with the overwhelmingly progressive thinking of most employees working on AI. 





Buy the EoZ book, PROTOCOLS: Exposing Modern Antisemitism  today at Amazon!

Or order from your favorite bookseller, using ISBN 9798985708424. 

Read all about it here!