Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hmokiguess
51 days ago
|
parent
|
context
|
favorite
| on:
LLM Problems Observed in Humans
You're absolutely right! (forgot that one)
fsflover
51 days ago
[–]
> reward hacking, where social approval or harmony is optimized at the expense of truth or usefulness
DenisM
51 days ago
|
parent
[–]
Blending is socially is very useful for the individual, i don’t agree with the author here.
Society itself may benefit from cohesion or from truth depending on circumstances.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: