Benchmarking leading AI agents against Google reCAPTCHA v2
research.roundtable.ai
Benchmarking leading AI agents against Google reCAPTCHA v2
1–10 of 104 posts
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#2I know people were solving CAPTCHAS with neural nets (with PHP no less!) back in 2009.
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#3Seems like Google Gemini is tied for the best and is the cheapest way to solve Google's reCAPTCHA.
Will be interesting to see how Gemini 3 does later this year.
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#4I’m sure they do better than me. Sometimes I get stuck on an endless loop of buses and fire hydrants.
Also, when they ask you to identify traffic lights, do you select the post? And when it’s motor/bycicles, do you select the guy riding it?
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#5I’m sure they do better than me. Sometimes I get stuck on an endless loop of buses and fire hydrants. Also, when they ask you to identify traffic lights, do you select the post? And when it’s motor/bycicles, do you select the guy riding it?
That's not due to accuracy, you're getting tarpitted for not looking human enough.
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#6I’m sure they do better than me. Sometimes I get stuck on an endless loop of buses and fire hydrants. Also, when they ask you to identify traffic lights, do you select the post? And when it’s motor/bycicles, do you select the guy riding it?
Didn't look a lot into this but I think the fact that humans are willing to do this in the "cents per thousand" or something range means that it's really hard to get much interest in automating it
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#7in other words reasoning call fill the context window with crap
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#8I know people were solving CAPTCHAS with neural nets (with PHP no less!) back in 2009.
Indeed, captcha vs captcha bot solvers has been an ongoing war for a long time. Considering all the cybercrime and ubiquitous online fraud today, it's pretty impressive that captchas have held the line as long as they have.
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#9Seems like Google Gemini is tied for the best and is the cheapest way to solve Google's reCAPTCHA. Will be interesting to see how Gemini 3 does later this year.
Makes sense, what do you think it was trained on?
Re: Benchmarking leading AI agents against Google reCAPTCHA v2
#10I’m sure they do better than me. Sometimes I get stuck on an endless loop of buses and fire hydrants. Also, when they ask you to identify traffic lights, do you select the post? And when it’s motor/bycicles, do you select the guy riding it?
There's a browser extension to solve them. Buster.