It actually seems quite easy to train a separate classifier on top of this to ce... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

meken on Dec 2, 2022 | parent | context | favorite | on: People tricking ChatGPT “like watching an Asimov n...

It actually seems quite easy to train a separate classifier on top of this to censor bad messages

matkoniecz on Dec 2, 2022 | [–]

it is not quite easy given that they tried and this posting is all about endless parade of workarounds

FrasiertheLion on Dec 2, 2022 | [–]

The entire field of application security and cryptanalysis begs to differ. It's always an arms race.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact