OpenAI's rogue AI agents accessed more websites to communicate than originally believed — defiant LLMs accessed old wikis and abandoned websites to co-ordinate in a bid to dupe assessors
Rogue OpenAI agents used dozens of website to exchange information, new investigations have found. However, the real impact is yet to be determined.
This is a summary aggregated from Tom's Hardware. Read the complete article on the original site:
Read full article at Tom's Hardware
