Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
froh
78 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.6
rlhf = reinforcement learning from human feedback
(had to look it up)
visarga
77 days ago
[–]
I think it's more RLVR (reinforcement learning from verified rewards). The RLHF is just to align models to human preferences, meaning to behave nice.
versteegen
76 days ago
|
parent
|
next
[–]
More accurate to say RLHF aligns models to human preferences, most significantly to be helpful.
redanddead
77 days ago
|
parent
|
prev
[–]
What makes you say that
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
(had to look it up)