CAPTCHAs can still detect AI agents
research.roundtable.ai
CAPTCHAs can still detect AI agents
1–10 of 76 posts
Re: CAPTCHAs can still detect AI agents
#2Until they learn to do that. So cat and mouse. So nothing new.
Re: CAPTCHAs can still detect AI agents
#3I’ve been using Claude Opus 4.7 with Chrome MCP, and it has worked successfully about 95% of the time. However, I’ve failed various hCaptcha challenges.
Re: CAPTCHAs can still detect AI agents
#4Until they learn to do that. So cat and mouse. So nothing new.
think the point is that they can't just "learn to do that", because to do so would mean solving human mind (that famously hasn't been going well)
Re: CAPTCHAs can still detect AI agents
#5Until they learn to do that. So cat and mouse. So nothing new.
think the point is that they can't just "learn to do that", because to do so would mean solving human mind (that famously hasn't been going well)
Well no, the idea is a tradeoff between interfaces and telemetry.
OK, the agents don't click in the same way as humans. You learn that, what about mouse hovering telemetry, time spent, etc. And one of the most extreme is to force biometrics - a lot of telemetry, breaks the interface a lot - but hey, you have assurance.
And none of these tradeoffs require understanding the deep processes of the human mind. Just, map is not the territory, how you do game the map harder and harder and how do the mapmakers respond to that?
Re: CAPTCHAs can still detect AI agents
#6I think it's just a game of cat and mouse. It might be easier to catch naive AI agents that are not fine-tuned for specific CAPTCHA tasks with human behavior, can't recognize new challenges, don't know when to stop and ask a human, and just want to brute force their way with limited or no specialized harness and tools available.
Re: CAPTCHAs can still detect AI agents
#7Earlier quoted context omitted.
think the point is that they can't just "learn to do that", because to do so would mean solving human mind (that famously hasn't been going well)
Well no, the idea is a tradeoff between interfaces and telemetry. OK, the agents don't click in the same way as humans. You learn that, what about mouse hovering telemetry, time spent, etc. And one of the most extreme is to force biometrics - a lot of telemetry, breaks the interface a lot - but hey, you have assurance. And none of these tradeoffs require understanding the deep processes of the human mind. Just, map i…
did you look at the paper? they specifically look at mini tasks with cognitive processes (Eg what dictates the strategy of how people solve tasks)
Re: CAPTCHAs can still detect AI agents
#8Apparently CloudFlare’s turnstile can’t, as evidenced by several public-facing CRUD and mail routines we maintain that no longer are warding off the spam.
Re: CAPTCHAs can still detect AI agents
#9Apparently CloudFlare’s turnstile can’t, as evidenced by several public-facing CRUD and mail routines we maintain that no longer are warding off the spam.
Meanwhile the moment I (a human, of which I'm reasonably confident) see a Cloudflare captcha I nope immediately out of the site and block it forevermore in Kagi. It's not worth the waiting game. "Verifying..." lasts ages.
The anime girl captcha works fine and provides no such annoyance.
Re: CAPTCHAs can still detect AI agents
#10Earlier quoted context omitted.
Well no, the idea is a tradeoff between interfaces and telemetry. OK, the agents don't click in the same way as humans. You learn that, what about mouse hovering telemetry, time spent, etc. And one of the most extreme is to force biometrics - a lot of telemetry, breaks the interface a lot - but hey, you have assurance. And none of these tradeoffs require understanding the deep processes of the human mind. Just, map i…
did you look at the paper? they specifically look at mini tasks with cognitive processes (Eg what dictates the strategy of how people solve tasks)
LLMs can solve original math problems at the IMO level and beyond, and you might be talking to one now. I don't think they are going to have problems with any CAPTCHA short of separate device attestation.
Whatever mechanism the paper proposes, rest assured it can be trained on.