HN Trends Tracker

backend ok

Repost history

Canonical URL: https://anthropic.com/research/emergent-misalignment-reward-hacking

Current story

#
Anthropic: Emergent Misalignment from Reward Hacking(anthropic.com)
HN #49,878,8062026-09-28 14:43 UTC
3 pointsby highfrequency28 days ago0 comments

#
Reward Hacking(anthropic.com)
HN #46,028,7882025-11-24 00:13 UTC
3 pointsby paulpauper337 days ago2 comments
#
Natural emergent misalignment from reward hacking(anthropic.com)
HN #49,534,6652026-09-02 11:19 UTC
1 pointsby tosh55 days ago0 comments