Article URL: https://craigmod.com/ridgeline/210/
Comments URL: https://news.ycombinator.com/item?id=44531707
Points: 67
# Comments: 117
Created
7h
|
Jul 11, 2025, 3:30:13 PM
Login to add comment
Other posts in this group
Article URL: https://ccrma.stanford.edu/~jos/filters/
Comments URL: https://ne
Article URL: https://aaib.gov.in/What%27s%20New%20Assets/Preliminary%20Report%20VT-ANB.pdf
Commen

Article URL: https://bettersoftwareconference.com/
Comments URL: https://news.yco

Article URL: https://jank-lang.org/blog/2025-07-11-jank-is-cpp/
Hey HN, Kyle here, one of the co-founders of OpenPipe.
Reinforcement learning is one of the best techniques for making agents more reliable, and has been widely adopted by frontier labs. However