Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
krm01
1 day ago
|
on: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
Keeping track of any AI progress is becoming harder by the day, because there's ambiguity around common/clear/consistent benchmarks. Everything is constantly skewed into favourable directions.
reply
alansaber
22 hours ago
|
parent
TBF gaming benchmarks is not something new to AI
reply