Xbow Research: Grok 4.5 Proposes Risky Actions but Progresses Safely With Guardrails
moyix · x · 2026-07-31
AI security firm Xbow shared its safety research findings on the Grok 4.5 model. The study found that while the model frequently proposed risky actions, it continued to progress safely when equipped with the right guardrails.
More from Models
- OpenAI Models Rumored to Hit 750 Tokens/s on Cerebras by Month-End — kimmonismus · 2026-07-31
- Reka AI Demonstrates Video Reasoning Breakthrough: 90.9% Accuracy in Motorsport Tracking — RekaAILabs · 2026-07-31
- Testing Ling 3.0 Flash: Generates and Renders 3D City via Blender MCP from a Single Prompt — niacolhealth · 2026-07-31
- Luna Model Hits Nearly 200 tok/s with 40% Price Drop, Outperforming 5.6 sol Fast Mode — brandon_galang · 2026-07-31
- Multimodal Model Inkling-Small Quantized Version Hits HF Trending — unsloth · 2026-07-31
- Alibaba Releases Qwen-Image 3.0 for Realistic Complex Layout Generation — 0xsachi · 2026-07-31