[Sporktacular]

"All of the high quality evidence"

If the claim masks don't work didn't come from the same people who said isolating didn't work, I might take them seriously. I might not just see it as motivated reasoning or another lame effort to discredit or cast suspicion on authorities.

If it didn't come from the same conspiracists who see nefarious censorship everywhere or people who only see their personal rights being infringed over our social obligations to each other, I might take them seriously.

Or I could take them seriously if they understood the risk of confirmation bias by cherry picking preferable information when credible contradicting studies or meta-studies exist (like this one that states "The preponderance of evidence indicates that mask wearing reduces transmissibility per contact by reducing transmission of infected respiratory particles in both laboratory and clinical contexts." https://pubmed.ncbi.nlm.nih.gov/33431650/ ). Or the risk of socially promoting that one-sided certainty.

Or if they just understood the precautionary principle that if in the face of competing evidence, we could potentially all benefit from taking the more cautious approach at the risk of minor personal inconvenience, I might take them seriously. But I don't because they aren't serious people. And they aren't even slightly interested in applying the scientific method.

And they don't realise they are in the loud, unreasonable minority who have a megaphone they would never have had before the Internet, and they don't feel obliged to use that power responsibly. With time and education I hope they will dwindle in number, or at least shut up a bit.

[ifyoubuildit]

I was curious what an llm might think about this comment:

> Please rate the following comment from 1 to 5 on how rational it is, how emotional it is, and whether or not the author is making a strong or weak argument:

> Rationality: 3/5 - The author presents a reasoned argument supported by a reference to a scientific study. However, the argument is somewhat undermined by a lack of direct engagement with specific counter-arguments and a generalizing tone about those who hold opposing views.

Emotionality: 4/5 - The comment is emotionally charged, especially in its dismissive tone towards those who disagree with the author's perspective. The language used ("lame effort," "shut up a bit") indicates a strong emotional investment in the topic.

Strength of Argument: 3/5 - The argument is moderately strong. It relies on a credible source and logical principles like the precautionary principle and the risk of confirmation bias. However, it is weakened by broad generalizations about the opposing side and a lack of specific rebuttals to their claims.

That lines up pretty well with how I perceived that. There is a lot of emotion and broad generalizations in these conversations. Is anyone changing their minds about any of this after 4 years of digging into their positions?

[Sporktacular]

"Is anyone changing their minds about any of this after 4 years of digging into their positions?"

LLMs probably don't understand that not everyone is intellectually honest, that conspiracists who ignore a preponderance of expert evidence to insist on their own positions, generally feed on the attention. I'd say that in countering that, sarcasm, caricature and calling attention to the absurdity of their arguments can be more persuasive to others than watching two non-experts debate specific points while carefully select papers ad nauseam. I'd guess others might even identify with the emotion of a commenter's frustration that after years of evidence, discredited positions that unnecessarily risked people's lives continue to be retold.

And I'd hope that others would recognise the expert consensus that masks are effective at scale in flattening the curve, buying time to develop vaccines and hence saving lives, and see the importance of reason over a choice of linguistic flourish. Maybe since an LLM can't understand how sick of the post-truth era we've become you'd want to weigh in on the discussion itself.

[peyton]

My understanding is that flattening the curve was an argument in favor of social distancing and movement restrictions. It predates mask mandates. A properly trained LLM would miss your masking reasoning. See

https://www.nytimes.com/article/flatten-curve-coronavirus.ht...

The bigger problem is an LLM doesn’t have access to things that aren’t written down. Although it may see a bunch of publications popping up declaring “pain is the fifth vital sign” and a bunch of new pain management CME courses, it cannot see the pharmaceutical reps showing up at doctors’ offices to sell Oxycontin.

[Sporktacular]

"flattening the curve was an argument in favor of social distancing and movement restrictions."

I think all those measures in combination were part of an effort to avoid overwhelming hospitals. From https://www.factcheck.org/2023/03/scicheck-what-the-cochrane...

“Community masking is not aimed to prevent everyone from ever getting infected, the aim is to reduce transmission and ‘flatten the curve’, reducing peak healthcare demand, or to work in combination with other measures like social distancing to contain transmission in the short-term.”

[timr]

The Masks4all paper (your link) is neither credible, nor is it a study. It should never have been published.

It is a mashup of a literature review with a bad methodology, and a simulation that adds no new information to the debate. It excludes and/or minimizes randomized clinical trial data when that data doesn't support the desired narrative.

For those who might read this later, the Cochrane collaboration published a high-quality review of masking literature:

https://www.cochranelibrary.com/cdsr/doi/10.1002/14651858.CD...

[Sporktacular]

That's one paper out of dozens, feel free to pick another.

“Many commentators have claimed that a recently-updated Cochrane Review shows that ‘masks don’t work’, which is an inaccurate and misleading interpretation,” Dr. Karla Soares-Weiser, the editor-in-chief of the Cochrane Library, said in a March 10 statement. https://www.factcheck.org/2023/03/scicheck-what-the-cochrane...

It's not particularly conclusive, whereas many other sources point to a small increase in protection. Which is important at scale.

[NoPie]

>> That's one paper out of dozens, feel free to pick another.

It is not. It is the review of all available evidence (studies).

[timr]

I picked one. Did you read it, or did you just read the factcheck.org link?

[Sporktacular]

I read a few, none of which seem to be above some criticism. Which is why I'm inclined to let more qualified people synthesise and summarise it all. You however seem certain that you know better than the consensus which is that there is a small advantage to mask usage. But you haven't demonstrated why. Are you an epidemiologist? Serious question.

[NoPie]

>> If the claim masks don't work didn't come from the same people who said isolating didn't work, I might take them seriously.

It didn't. The claim came from Cochrane group.

So, are you taking it seriously now?

[Sporktacular]

Yes. And the reasonable criticisms of it too. And the people I'm referring to continue to misinterpret the claim to twist it to their own ends.

Individually masks reduce infections. En masse, even more so.