@Jack_W_Lindsey To be really direct, the fear is this framing of the paper induces is that Anthropic thinks assistant = good, non assistant = bad, and you’re going to steer Claude like you steered…

Posters: repligate. repligate

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/repligate/status/2013416635931992153