Navigation
Recherche
|
ChatGPT joins human league, now solves CAPTCHAs for the right prompt
vendredi 19 septembre 2025, 20:20 , par TheRegister
Could this bot-prevention technique now be obsolete?
ChatGPT can be tricked via cleverly worded prompts to violate its own policies and solve CAPTCHA puzzles, potentially making this human-proving security mechanism obsolete, researchers say.…
https://go.theregister.com/feed/www.theregister.com/2025/09/19/how_to_trick_chatgpt_agents/
Voir aussi |
56 sources (32 en français)
Date Actuelle
sam. 20 sept. - 01:39 CEST
|