Reaction
Whose values should AI models align with: labs’ or users’?
A post questions whose values guide frontier labs’ AI alignment. A reply argues that some users want to do dangerous things.
TLDR
One post asks why frontier labs would align models to their own values rather than users’ values. A reply argues that some users want to do dangerous things. A separate quote post claims that seeking control in the name of alignment and safety can be a pretext for securing power for self-interest.
Combined views
231.2K
4 Sources, first seen ago
6.7K likes375 comments319 saves788 reposts
