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.
More from Models
- OpenAI Voice Update Adds French, German, Hindi, Korean, Japanese Voices and Naturaler Preambles — shaunralston · 2026-10-16
- Why aren't labs training on hundreds of millions of videos for native audio/video? — imjustnewatai · 2026-10-16
- ChatGPT UI screenshot reveals Wallet coming soon plus Email, Calendar, Health and Finances integrations — jxnlco · 2026-10-16
- Why the next OpenAI and Anthropic models may still disappoint: no native audio or video input — imjustnewatai · 2026-10-16
- Thousands Hit by ChatGPT Standard Voice Mode Regression: Wrong Voice, Interruptions — shaunralston · 2026-10-16
- Gemini Argon 4 Quota Exhausted, Reset Countdown Shows Nearly 7 Days — ssh4net · 2026-10-16