This does not distract from the potential usefulness of the effort, since the work does not at all depend on some word's definition, so this is merely a side note, "FYI": It appears that the "common" in common sense does not exist. It could only be found in "plainly worded, factual claims about physical reality"; "We also find limited presence of collective common sense, undermining universalist claims and supporting skeptics." (from the study abstract).
> Common sense is not that common: a recent study from the University of Pennsylvania concludes the concept is “somewhat illusory”. Researchers collected statements from various sources that had been described as “common sense” and put them to test subjects.
> The mixed bag of results suggested there was “little evidence that more than a small fraction of beliefs is common to more than a small fraction of people”.
What this study does show that is relevant for the submitted article is that whatever he trains the AI for, it may not be something "common".
I think nitpicking the commonness of common sense is taking the term a bit too literally. I see it as another way to talk about intuition or gut feelings; knowledge that has some uncertain or wishy-washy origin, probably an amalgamation of experience (which naturally differs for everybody) and informal automatic reasoning (which may often err, but is nonetheless important for the way people navigate life because it can be done more efficiently than more rigorous reasoning.)
This isn't nitpicking, what are you talking about!?
When someone tries to give an AI "common sense" talking about exactly what I said is important! Because that person is NOT going to do anything "common", (s)he is implementing their own version and biases!
That distinction is at the very heart of the matter attempting to be achieved, not some "nitpicking" about terms!
I am not really on board with this study's interpretation of common sense - it seems to measure how close the things that I think are to the average. Which is a very literal take on 'common' sense. Considering the tests have a ton of questions about spirituality, and advanced technologies, for me the exercise devolved into trying to guess what others would think of it (which turned out to be the point after all).
And the author's person seems really concerning. She is someone, who, by her own admission struggles with grade school math such as fractions, yet proclaims her intellectual superiority over people who think 'obviously' silly things, like Ivermectin curing covid.
The idea of horse medicine curing Covid makes about as much sense as heart medicine helping with erections.
Although, somewhat amusingly, she seems to score below average on the common sense test.
The very cynical take of journalists being both substandard critical thinkers, and unwilling consider alternative viewpoints seems to be true in this case.
Why should it be nonsense? Erections are a function of the circulatory system. One could expect them improve if the circulatory system is improved as well.
https://www.theguardian.com/commentisfree/2024/sep/30/i-took...
The article links to the study.
> Common sense is not that common: a recent study from the University of Pennsylvania concludes the concept is “somewhat illusory”. Researchers collected statements from various sources that had been described as “common sense” and put them to test subjects.
> The mixed bag of results suggested there was “little evidence that more than a small fraction of beliefs is common to more than a small fraction of people”.
What this study does show that is relevant for the submitted article is that whatever he trains the AI for, it may not be something "common".