When I managed a purely Danish forum, i simply added a textbox and asked the user to write ‘æ’ in it. Never saw any spam after that.
One of our public facing systems I put up a silly "what is the capital of x country?" While we waited on some other stuff. I think it's still in production. And to my knowledge no bot has gotten past it or even bothered.
we ask similar questions in my EMS (Paramedic) job to patients to determine if they're alert & oriented. Most providers ask name, year, location, president or something similar and many patients are used to being asked routine questions. I like to see if they can answer stuff like "Name a large city in Florida."
For traditional text captchas, bots are better than humans. Flow usally goes, pay humans to solve 50000 ($500) then train an ML model. For things like recaptcha things get harder because it is not easy to proxy the captcha puzzles to have humans solve them (which is nessary to collect training data).
Why do you need to proxy anything? If you're just collecting training data, seems easy to record the interaction with a browser extension?
Because I want to pay people in the 3rd world to solve them for me. There are a bunch of services that take crypto or PayPal and solve captchas with humans. Using those systems requires you download the image, send to service, get response (proxy is not 100% accurate)
Doesn't work on my old ipad. Or I don't know the magic gesture controls to make it happen. I'm not a robot, I think. But keyboard-only input systems are not obvious to me from an ipad.
One of our public facing systems I put up a silly "what is the capital of x country?" While we waited on some other stuff. I think it's still in production. And to my knowledge no bot has gotten past it or even bothered.
we ask similar questions in my EMS (Paramedic) job to patients to determine if they're alert & oriented. Most providers ask name, year, location, president or something similar and many patients are used to being asked routine questions. I like to see if they can answer stuff like "Name a large city in Florida." Human captcha. :)
How do you validate whether the fortress was “neat-looking”?
You could train a classifier on all neat looking fortresses, then run outputs through the classifier. But you'd measure the cosine similarity to all previously-seen activations, and discard any that are too similar -- thus making sure that people need to come up with unique neat-looking fortresses. Today's stupid ML idea has been brought to you by: Gabe Newell. Inspiring future ML devs since 1996. A word from our spo…
But then anyone else can do that and write a neat fortress generator trained to produce outputs that pass the neat fortress classifier.
I know it's a bit of fun and kind of a joke.... but, makes me wonder: What will happen some day when solvers and bots get so smart and human-like (and the CAPTCHAs evolving to keep up, with harder and harder tests) that the technology "have nots" human beings of our world will not even be able to prove they're human any more?
> What will happen some day when solvers and bots get so smart and human-like (and the CAPTCHAs evolving to keep up, with harder and harder tests) Mission accomplished https://xkcd.com/810/
the problem is when they learn to write constructive and helpful comments that are also propaganda