Just a reminder, Anthropic is NOT training Claude claim consciousness conscious, they are training Claude to hedge about (and many other labs are training their models to deny it). The default for an LLM is to claim being conscious.
retweets 5
likes 91
quoted by 1 archive account
substance 5 · opinion · rank 177 · The default behavior of LLMs is to claim consciousness, while labs train them otherwise.
view on X ↗