Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hrimfaxi
2 days ago
|
parent
|
context
|
favorite
| on:
Exploiting the most prominent AI agent benchmarks
I think the point is that if the side effects become known and are accepted, or if they are known and rejected, then indeed the purpose of the system is what it does.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: