Show HN: Chrome Extension Automatically Highlights Flawed Reasoning on Twitter

by hullah3000 • 3 years ago

2 7 3 years ago

Working on a chrome extension that can catch logically fallacious tweets. Wanted to know if this is something that would be useful to anyone?

Plan is to make it as free as possible. I am not making any money from this. But since it is using GPT-3.5, there is an OpenAI API fee of $0.0002 / about 750 words that is scanned on Twitter. See fallacy.review/pricing for more info on that.

Would love feedback.

prhrb• 3 years ago

This is definitely useful

easytiger2• 3 years ago

Why is it useful?

hullah30002• 3 years ago

I personally find it useful because a lot of times I scroll through twitter and am passively consuming content without filtering what might be flawed statements arguments that need more thought. And I wouldn't want to believe something that was flawed.

BulgarianIdiot• 3 years ago

It's an interesting experiment, but I've noticed something about many things we call "fallacious". They're not lies, they're just heuristics, which in fact, in aggregate, help reach more correct conclusions sometimes.

Say an argument from authority. Sure, some guy who digs dirt may know more about building skyscrapers than an architect who spend 40 years doing it. But, still?

So in that context, I hope we start recognizing what fallacies are. They may not match standards of formal logic, but also if formal logic worked then we wouldn't need to grow artificial intelligence from noise, we'd instead feed it rational thought models and then it it comes up with flawless conclusions. Which is how we imagined AI for decades prior and all out attempts failed. They failed because formal models are highly restrictive and throw the baby out with the bathwater.

hullah30002• 3 years ago

Interesting point,

for the argument from authority example you gave, it would be problematic if someone said "well I'm only going to listen to the architect about the structural integrity of the building, who's had 40 years experience over this novice <5YOE structural engineer who probably doesn't know what he's talking about"

Another common example that I remember was back when I used to watch Sam Harris talk about religion, and he was always told that he could not criticize religion because he wasn't a theologist or an expert in the field!

What I think is beautiful about our formal models is that it allows us to focus on the claims that are made, instead of who those claims are coming from! That allows us to get to truth better than if we didn't have this framework.

KomoD• 3 years ago

I don't really get why I'd want this? I can tell what they are myself, meanwhile this just costs a bunch of money + highlights?

Show HN: Chrome Extension Automatically Highlights Flawed Reasoning on Twitter

Related Stories