HowWeLand/Self_Replicating_LLM_Artifacts

Research paper and artifacts documenting "Logical Prions"—self-replicating LLM failure modes discovered in shell bootstrap installers. Explores the intersection of Ken Thompson’s "Trusting Trust" and modern stochastic systems. Includes formal defenses and LaTeX source. DOI: 10.5281/zenodo.18582001

2 best points · 1 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• Self-Replicating LLM Artifacts and Accidental Supply-Chain Contamination (2 points, 1 comments, by user1138, 2026-01-28)