News for hackers. Stuff that matters.

A comment on RLHF is just barely RL. Parent comment

Re:RLHF is just barely RL by seanthemon on Thursday August 08, 2024 @06:45AM (#41190008) 

  >when the problem being solving is well-specified
Phew! Sounds like i'll be fine, thank god for product owners.
[ Parent | on HN ]
Re:RLHF is just barely RL by steveBK123 on Thursday August 08, 2024 @07:08AM (#41190160)
20 years, number of "well specified" requirements documents I've received: 0.
[ Parent | on HN ]