[–] bit_byte 2y ago ↗ Check out the AI safety comparison between Llama2, Mistral GPT-4, GPT-3.5, using TigerLab toolkit
[–] nradov 2y ago ↗ None of those test cases have anything to do with actual safety. LLMs haven't shot anyone yet.
2 comments
[ 3.0 ms ] story [ 14.5 ms ] thread