Re:All the ways to get around ChatGPT's safeguards
by dr_kiszonka on Wednesday December 14, 2022 @10:11AM
(#33984472)
I think there may be different ways to do that, from new models (as you wrote) to simple filters. For example, I couldn't get ChatGPT to output any real examples of hate speech. They may have a filter that picks up candidate responses with hate speech and blocks them.
[ Parent
| on HN ]
There are no comments on this comment yet.