Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ThrowawayTestr
3 days ago
|
parent
|
context
|
favorite
| on:
Invisible text that AI chatbots understand and hum...
The vuln is that a user can be tricked into exfiltrating data without it being obvious.
ForHackernews
3 days ago
[–]
But what "data"? LLMs don't know anything except whatever they were trained on, right?
reply
probably_wrong
3 days ago
|
parent
[–]
The article describes how the content of a document (which in theory should only be sent to OpenAI) can be exfiltrated to an attacker via URL parameters.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: