Conversation

Notices

1. Embed this notice
   Lup Yuen Lee 李立源 (lupyuen@qoto.org)'s status on Wednesday, 03-Apr-2024 11:23:25 JST Lup Yuen Lee 李立源

   "a Large Language Model (#LLM) can be convinced to tell you how to build a bomb if you prime it with a few dozen less-harmful questions first"

   https://techcrunch.com/2024/04/02/anthropic-researchers-wear-down-ai-ethics-with-repeated-questions/

   • Embed this notice
     🎓 Doc Freemo :jpf: 🇳🇱 (freemo@qoto.org)'s status on Wednesday, 03-Apr-2024 11:23:18 JST 🎓 Doc Freemo :jpf: 🇳🇱

     in reply to

     @lupyuen I actually have no issue with AI or anything else instructing people on how to make bombs. Knowledge should never be illegal.

   • Embed this notice
     ampbenzscientist@qoto.org's status on Wednesday, 03-Apr-2024 12:13:14 JST AmpBenzScientist

     in reply to

     • 🎓 Doc Freemo :jpf: 🇳🇱

     @freemo @lupyuen I don't see the problem except that it didn't specify if it was fission, fission-fusion or pure fusion.

     Conventional energetic devices are just containers that fail to hold a chemical reaction.

     There's even an argument that not knowing how to make a bomb is worse. For example a young agent finding a rental van with a lot of fertilizer and saying that it's fine exactly a year after setting a residence on fire and massacring a religious community.

     Or making a funny tiktok where a glitter prank goes in an unexpected direction because they used aluminum powder.

     "A little learning is a dangerous thing; drink deep, or taste not the Pierian spring." Alexander Pope