@lumpenspace Systems like GPT-4 are basically AGI but not yet scary agents. Can we use GPT-4 and its successors to help us solve the alignment problem, and if so, how?

Posters: repligate. repligate

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/repligate/status/1642926907279785985