Replication problems raised for Palisade's AI self-replication study

NathanpmYoung · x · 2026-11-19

Palisade Research, an AI safety nonprofit, published a study in May 2026 claiming language models can autonomously replicate their weights and harness across a network by exploiting vulnerable hosts. A new article now raises replication problems with the study, challenging its conclusions. The poster, who has followed the issue closely, finds the error magnitudes hard to judge and awaits the authors' response.

Related event: Palisade's AI Self-Replication Study Faces Replication Challenges(2 posts)→

Original post →

More from Safety

Safety channel →