I can only imagine how much worse they'll make the captcha after stuff like this picks up speed with the users all the while being ineffective against the bots.
I really doubt that they're the first to do this.
Breaking the 4Chan CAPTCHA
11–20 of 378 posts
Re: Breaking the 4Chan CAPTCHA
#12It might be worth noting that this, including the harder version the op encountered, are not the hardest captchas that 4chan can serve. There is a still harder version which is sent to less trustworthy IPs. I imagine it would still be tractably solved with computer vision. This in part misses the point though, since 4chan has been continuously altering their captcha since it released, making it difficult to create a permanent solution that won't be broken down the road.
Re: Breaking the 4Chan CAPTCHA
#13Appropriate response by 4Chan to this: simplify the human work given that anyway it's simple to solve via NNs. We are at a point where designing very hard captchas has high probabilities to increase the human annoyance without decreasing the machine solvability.
Re: Breaking the 4Chan CAPTCHA
#14Re: Breaking the 4Chan CAPTCHA
#15It might be worth noting that this, including the harder version the op encountered, are not the hardest captchas that 4chan can serve. There is a still harder version which is sent to less trustworthy IPs. I imagine it would still be tractably solved with computer vision. This in part misses the point though, since 4chan has been continuously altering their captcha since it released, making it difficult to create a…
Yeah, I encountered those as well in my data gathering. I threw them out from the training set, but I kept them for possible future experimentation.
Re: Breaking the 4Chan CAPTCHA
#16 > The official TensorFlow-to-TFJS model converter doesn't work on Python 3.12. This doesn't seem to really be documented, and the error messages thrown when you try to use it on Python 3.12 are non-obvious. I tried an older version of Python (3.10) on a hunch, using PyEnv, and it worked like a charm.
Re: Breaking the 4Chan CAPTCHA
#17It might be worth noting that this, including the harder version the op encountered, are not the hardest captchas that 4chan can serve. There is a still harder version which is sent to less trustworthy IPs. I imagine it would still be tractably solved with computer vision. This in part misses the point though, since 4chan has been continuously altering their captcha since it released, making it difficult to create a…
Yeah, I encountered those as well in my data gathering. I threw them out from the training set, but I kept them for possible future experimentation.
Can you upload a few of these samples somewhere?
Re: Breaking the 4Chan CAPTCHA
#18> The official TensorFlow-to-TFJS model converter doesn't work on Python 3.12. This doesn't seem to really be documented, and the error messages thrown when you try to use it on Python 3.12 are non-obvious. I tried an older version of Python (3.10) on a hunch, using PyEnv, and it worked like a charm. Amazing. And then people wonder why "just use python 2" is still a thing.
Do you have examples of "just use python 2" still being a thing in 2024?
Re: Breaking the 4Chan CAPTCHA
#19I can only imagine how much worse they'll make the captcha after stuff like this picks up speed with the users all the while being ineffective against the bots.
I mean at some point ... the average visitor is dumber than the AI and your now just blocking dumb people
Re: Breaking the 4Chan CAPTCHA
#20I can only imagine how much worse they'll make the captcha after stuff like this picks up speed with the users all the while being ineffective against the bots.
captchas are broken, forever. There is no way to prevent bots without also preventing a bottom tier of human users (visually impaired people, old people, or just impatient people). Like this xkcd [1] comic suggests, we need to just focus on rewarding and punishing specific behavior, regardless of whether the agent is human or not