Granite Guardian
PulseAugur coverage of Granite Guardian — every cluster mentioning Granite Guardian across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Granite Guardian Outperforms Llama Guard in Multilingual and Regulated LLM Safety
Llama Guard and Granite Guardian are two open-weight safety classifiers for LLMs, but they differ significantly in their capabilities and licensing. While Llama Guard excels at content safety and is suitable for English…
-
New defenses and benchmarks tackle malicious Generative Engine Optimization in search · 4 sources tracked
Researchers have developed new methods to defend generative search engines against malicious Generative Engine Optimization (GEO), a technique used to manipulate search results. One approach, GEO Defender, uses a two-st…
-
AI safety models vulnerable to fine-tuning and embedding bypass attacks
Two new research papers explore vulnerabilities in AI safety mechanisms. The first paper, "When Safety Geometry Collapses," demonstrates how fine-tuning even benign guard models can inadvertently destroy their safety al…