RLHF is just barely RL

Re:RLHF is just barely RL by dartos on Thursday August 08, 2024 @09:30AM (#41191280)

We’ve also learned that starting off by rigidly defined spec is actually harmful to most user facing software, since customers change their minds so often and have a hard time knowing what they want right from the start.

[ Parent | on HN ]

Re:RLHF is just barely RL by diffxx on Thursday August 08, 2024 @01:39PM (#41194193)

This is why most of the best software is written by people writing things for themselves and most of the worst is made by people making software they don't use themselves.

[ Parent | on HN ]

Re:RLHF is just barely RL by TZubiri on Friday August 09, 2024 @07:27AM (#41200783)

True facts: half of the self made software are task trackers.

[ Parent | on HN ]

Re:RLHF is just barely RL by dartos on Monday August 12, 2024 @08:16AM (#41223553)

Sure, and the most performed song in the world is probably hot cross buns or Mary had a little lamb.

[ Parent | on HN ]