xAI Accused of Omitting Safety and Prompt Injection Robustness Results

npinto · x · 2026-08-13

Researchers have noticed that xAI's recent model technical report is missing several key sections, including robustness against prompt injection and various safety evaluation results (specifically sections 3.3, 4.5, 4.6, and 4.7).

This omission has sparked concerns and skepticism within the AI community, with critics questioning whether xAI is deliberately hiding underperforming safety metrics or avoiding transparency in its model evaluations.

Original post →

More from Models

Models channel →