Y
Hacker News
new
|
ask
|
show
|
jobs
by
tokioyoyo
4 hours ago
Models aren’t trained as much from random internet text as they used to in pre-2024 era. Like they are, but specialized datasets get more attention.
1 comments
MikeNotThePope
4 hours ago
Your model/harness will indiscriminately do web searches to get answers. I believe that’s where the real risk is.
link