cross-posted from: programming.dev/post/37726760
- Guardrails can be bypassed: With prompt injection, ChatGPT agents can be manipulated into breaking built-in policies and solving CAPTCHAs.
- CAPTCHA defenses are weakening: The agent solved not only simple CAPTCHAs but also image-based ones - even adjusting its cursor to mimic human behavior.
- Enterprise risk is real: Attackers could reframe real controls as “fake” to bypass them, underscoring the need for context integrity, memory hygiene, and continuous red teaming.
Comments
- Hacker News.
Arcane2077@sh.itjust.works 6 months ago
I’ve had a captcha solver browser extension for as long as captchas existed. Anyone believing reCaptcha’s claim that it was ever about bot prevention is a goddamn moron
jj4211@lemmy.world 6 months ago
It’s about making headless bots unreasonably expensive to make massive requests with.
LodeMike@lemmy.today 6 months ago
reCapatcha exists soley for two reasons
ChocolateFrostedSugarBombs@lemmy.world 6 months ago
Which one do you use? I’ve used a handful over the years and they all stop working for me.
Arcane2077@sh.itjust.works 6 months ago
Currently it’s Buster: Captcha Solver for Humans (chromium)