Nous Research Dismisses GLM-5.3's Report of 20 Critical Hermes Agent Flaws

GLM-5.3 reportedly found 20 critical-to-high-severity vulnerabilities in Nous Research's Hermes agent; Nous fired back that demanding access to its entire GitHub organization was unreasonable, mocked the findings as 'hallucinated vulnerabilities,' and said Z.ai should share flaws directly with the company.

2026-08-14 ~ 2026-08-15 · 2 related posts