Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
andrepd
4 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.2
"Benchmarks" for LLMs are a total hoax, since you can train them on the benchmarks themselves.
XCSme
3 days ago
[–]
I would assume a good benchmark has hidden tests, or something randomly generated that is harder to game
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: