Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I Built Paul Graham's Intellectual Captcha Idea

mentwire.com

Post reply on HN
Print view View original

1–10 of 49 posts

Show HN: I Built Paul Graham's Intellectual Captcha Idea

#1

Post by nowflux »

PG has posted about improving social networks using something like an "intellectual CAPTCHA" many times [1][2][3][4] - "Make users pass a test on basic concepts like the distinction between necessary and sufficient conditions before they can tweet."

I felt the same way. So I built one using a mix of simple math, logic, and Twitter/X Community Noted posts. Try sample questions here - https://mentwire.com/sample - without signing up.

- Invites are temporarily open to HN users.

- Onboarding test + one daily question before accessing feed, post or reply.

- Posts authors are anonymous until upvoted or downvoted, forcing evaluation of content on merit.

- Face ID (on-device only) to post/reply, pangram checks for AI text.

Sourcing good questions turned out to be much harder than I thought. If you have suggestions to scale this, I would love to hear. Eventually, could be gated across disciplines/topics to get a competence × interest graph instead of the pure interest graph of today's social networks.

[1] https://x.com/paulg/status/1235949761359904768 [2] https://x.com/paulg/status/1576517990182359040 [3] https://x.com/paulg/status/1514979883948126209 [4] https://x.com/paulg/status/1505842647319126016

Repost from https://news.ycombinator.com/item?id=47577829.

This link contains a full quiz and linked directly to sample to try without signing up.

Show HN: I Built Paul Graham's Intellectual Captcha Idea
mentwire.com

Re: Show HN: I Built Paul Graham's Intellectual Captcha Idea

#2

Post by philipkglass »

At least one of the test questions was just a screen shot from a tweet. It was difficult to read. I'd suggest extracting text from screen shots with OCR. Apple has built-in functionality for this on their operating systems with Live Text. There are strong open source systems based on small vision language models for this, too. The one I have been recommending lately is GLM-OCR:

https://github.com/zai-org/GLM-OCR

It's fast and can run even on low-resource computers.

---

Does this CAPTCHA actually resist computers? I didn't try feeding the questions I got to an LLM, but my sense is that current frontier models could probably pass all of these too. Making generated text pass the pangram test is simple enough for someone actually writing a bot to spin up automated accounts.

Re: Show HN: I Built Paul Graham's Intellectual Captcha Idea

#3

Post by _alternator_ »

Two mild concerns: first, I missed one and it told me I didn’t miss any at the end.

Second, some of the logic problems have flawed premises (eg All licensed pilots must pass a medical exam. Jake is a licensed pilot, therefore Jake passed a medical exam.) If you see the flaw in the premise (it assumes no fraud) then the conclusion does not follow.

Im not sure you’re going to be able to actually improve human discourse this way. The idea that it’s ‘irrationality’ that’s the source of xitters problems is far too shallow to really make a change.

Re: Show HN: I Built Paul Graham's Intellectual Captcha Idea

#5

Post by metalliqaz »

it's a really nice idea, but of course completely antithetical to the business model of modern social media platforms. So, it will never go anywhere. HN might be the only locale with any real numbers that I could see actually using it. Even BlueSky I think could never risk something like this.

as an interesting thought experiment, consider the questions that TruthSocial would put in. would an average unsophisticated user be able to tell the difference between your product and a hopelessly biased version such as that? they would support the correct answers with their own misinformation. Would it be just another schism of reality?

Re: Show HN: I Built Paul Graham's Intellectual Captcha Idea

#6

Post by tripplyons »

philipkglass wrote: post #2

At least one of the test questions was just a screen shot from a tweet. It was difficult to read. I'd suggest extracting text from screen shots with OCR. Apple has built-in functionality for this on their operating systems with Live Text. There are strong open source systems based on small vision language models for this, too. The one I have been recommending lately is GLM-OCR: https://github.com/zai-org/GLM-OCR It's…

I think it's more about resisting some humans than it is about resisting machines.

Re: Show HN: I Built Paul Graham's Intellectual Captcha Idea

#8

Post by rogual »

_alternator_ wrote: post #3

Two mild concerns: first, I missed one and it told me I didn’t miss any at the end. Second, some of the logic problems have flawed premises (eg All licensed pilots must pass a medical exam. Jake is a licensed pilot, therefore Jake passed a medical exam.) If you see the flaw in the premise (it assumes no fraud) then the conclusion does not follow. Im not sure you’re going to be able to actually improve human discourse…

I took the pilot one as an abstract logic type question where you're supposed to assume the premise is true, so I said yes and the page said I was right, because that's a "valid logical deduction" or something.

Then there was another question in the same format that said "if you study hard enough you'll pass the exam. You didn't pass, so you didn't study hard enough." So I thought, oh, another logic one, and said yes to that one too, but the page was like, "not quite! You might fail for other reasons!"

Post reply on HN