Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
abcde88's comments
login
abcde88
6 months ago
|
parent
|
context
|
next
[–]
| on:
Why We Think
dnr
abcde88
10 months ago
|
parent
|
context
|
prev
[–]
| on:
Sycophancy in GPT-4o
I've seen the same behavior in Gemini. Like exactly the same. It is scary to think that this is no coincidence but rational evolution of A model, like this is precisely the reward model which any model will lean to with all the consequences.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: