Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
semanticintent
88 days ago
|
parent
|
context
|
favorite
| on:
Exploiting the most prominent AI agent benchmarks
[flagged]
esperent
88 days ago
[–]
> A validator that checks "did the assistant reply?" instead of "was the reply correct?" was never a benchmark. It was a participation trophy
People can't even write a two paragraph comment without ai now
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: