Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nneonneo
on May 20, 2023
|
parent
|
context
|
favorite
| on:
Don Knuth plays with ChatGPT
It’s really hard for the model to throw off that RLHF training, and I’m guessing they’ve made it even harder after people kept trying to jailbreak it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: