Peter Hroššo

Karma: 68

LLM keys—A Proposal of a Solution to Prompt Injection Attacks

Peter Hroššo7 Dec 2023 17:36 UTC

1 point

2 comments1 min readLW link

CAIS-inspired approach towards safer and more interpretable AGIs

Peter Hroššo27 Mar 2023 14:36 UTC

13 points

7 comments1 min readLW link

My summary of the alignment problem

Peter Hroššo11 Aug 2022 19:42 UTC

15 points

3 comments2 min readLW link

(threadreaderapp.com)