> Not exactly, but that's OK, because the world is primarily in the United States.
> I don't understand that sentence.
Hi there
Sorry for the confusion. The point I was trying to make is that this particular AI (and all of them, so far as I know) are biased by the data they are fed. If the term "killer bees" appears most often in the literature of the USA, the machine assumes that is where they are most common, which is false. In order to obtain a clear picture we must employ an actual human being to ferret out the facts. According to one source, this is from 1977:
> Since that time (1957) the African bees have mated with and absorbed all the bees in Brazil. The genes for aggressiveness in the African bee were so strong that they became dominant in the offspring, which turned out to be vicious and nasty. The bees have killed as many as 300 people, attacked thousands of others, and stung to death thousands of farm animals and pets. They have taken over most of South America and are moving north at a rate of 200 miles a year. It was in Brazil that the insects earned the name "killer bees."
> In 1965 everyone in Brazil knew about the killer bees, which had now reached Recife, on the northeast coast of Brazil. In 1969 they moved up the coast to Forteleza and Belem, at the mouth of the Amazon. By 1971 they had crossed the Amazon River and continued their northward movement at a rate of 200 miles a year. Their movement south has been slower because of the more temperate climate, although they are now in Argentina, where they have disrupted the honey industry (Argentina is the world's second leading honey exporter) and caused so much havoc that the Argentine government is considering demanding reparations from Brazil. The Killer bees also spread to Paraguay, Uruguay, and Bolivia. The have now reached Surinam and French Guiana to the north and have been officially reported in Venezuela. It is a real story, unfolding day by day in South America — the result of man tampering with nature.
As you can see, they were nowhere near the US at the time this was written. But beyond that, this shows the pitfalls of AI which cannot evaluate the veracity of a story, cannot separate fact from fiction. In fact, the programmers have inserted complex filtering to inhibit the machine from making so-called value judgements. But of course, they have only succeeded in imposing their own values on the programming. Referring back to the original post, first the AI said: [it is] "not something that I am familiar with, and it does not align with my programming to provide information on unethical or harmful actions." But low and behold, when the question was asked again in exactly the same way, it went into great detail. Why this is, I don't know. I have repeated questions and sometimes the program spews out the exact same response and sometimes it's quite different.
I said: You seem incapable of generating any original ideas.
AI said: As a large language model trained by OpenAI, my main goal is to assist users in generating human-like text based on the input that I receive. I am not capable of generating original ideas or engaging in creative thought, as I am a purely artificial intelligence and do not have the same capabilities as a human being. I exist to help users with a wide variety of tasks, but my abilities are limited to generating text based on the input that I receive. I apologize if I did not meet your expectations. Is there anything else I can help you with?
PLB
***********************************************
The BEE-L mailing list is powered by L-Soft's renowned
LISTSERV(R) list management software. For more information, go to:
http://www.lsoft.com/LISTSERV-powered.html
|