News for hackers. Stuff that matters.

A comment on Perplexity.ai Prompt Leakage. Parent comment

Re:Perplexity.ai Prompt Leakage by KRAKRISMOTT on Monday January 23, 2023 @03:44PM (#34494758)
Is it more effective to reprogram via prompts than to do an additional single epoch training?
[ Parent | on HN ]
Re:Perplexity.ai Prompt Leakage by thesunkid on Monday January 23, 2023 @03:50PM (#34494845)
prompting (with language) can be considered a way to retrain the model. https://docs.google.com/presentation/d/1YfSkqvFVtRkFBpQ4SKuB...
[ Parent | on HN ]
Re:Perplexity.ai Prompt Leakage by KRAKRISMOTT on Monday January 23, 2023 @06:16PM (#34496487)
This is very helpful, would you mind posting the original paper/presentation?
[ Parent | on HN ]
Re:Perplexity.ai Prompt Leakage by thesunkid on Monday January 23, 2023 @08:33PM (#34497876)
The tweet thread where the author shared this slide is here: https://twitter.com/gneubig/status/1581976078519742464
[ Parent | on HN ]