Testing Perplexity AI

On of the problems with Large Language Models, or as the kids say "AI", is that these models tend to hallucinate but present their information with a certain resoluteness or self assuredness that can be mistaken for actually knowing the facts. 

The team behind Perplexity AI tried to tackle this by forcing the LLM to include copious amounts of links to the sources of the quilted information. Kagi's FastGPT is following a similar solution. 

I was pleasantly surprised when I tried this query:

What is deionized water?

https://www.perplexity.ai/search/What-is-deionized-cmH_mSEuQ6qcxRYqdevi5Q

A short history of saturated fat: the making and unmaking of a scientific consensus - PMC

So eating butter is healthy after all?

It's like all the health nuts have been telling us for years 🤔 

The idea that saturated fats cause heart disease, called the diet-heart hypothesis, was introduced in the 1950s, based on weak, associational evidence. Subsequent clinical trials attempting to substantiate this hypothesis could never establish a causal link. However, these clinical-trial data were largely ignored for decades, until journalists brought them to light about a decade ago. Subsequent reexaminations of this evidence by nutrition experts have now been published in >20 review papers, which have largely concluded that saturated fats have no effect on cardiovascular disease, cardiovascular mortality or total mortality. 

Link:  https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9794145/