Y
Hacker News
new
|
ask
|
show
|
jobs
by
tuhgdetzhh
122 days ago
Source?
1 comments
tverbeure
122 days ago
I don't know, but model names such as "kimi-k2-thinking" in the test set might offset a clue.
link
etyhhgfff
122 days ago
Yes, there are some exceptions where it clearly states that a thinking model has been chosen like for kimi, but there is no such indicator for the GPT family from OpenAI and other major models.
link