arXiv - CSCL
Follow

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark. (arXiv:2304.03279v4 [cs.LG] UPDATED) 

arxiv.org/abs/2304.03279

· · arxiv-cscl · 0 · 0 · 0
Sign in to participate in the conversation
CleverLibre Social

CleverLibre Social is an inclusive social instance for open discussion, learning, and community.
All cultures welcome.
Hate speech and harassment strictly forbidden.

Trending now

Resources

Developers

What is Mastodon?

social.cleverlibre.org

More…

v3.5.19-qoto · Privacy policy