Appier today announced new research advancing the reliability of Agentic AI systems. To expand the impact of its research and ...

Udit Joshi’s reputation for rigor has made him a sought-after voice for industry benchmarks. He currently serves as a judge ...

The A-D-A-E framework is a governance model that injects ESG accountability, enterprise risk management, regulatory ...

Founded in 2024, Promptfoo began as an open-source framework for evaluating AI prompts and model behavior. It later expanded into a commercial platform used by developers and enterprise security teams ...

What if building smarter, more reliable AI agents wasn’t just about innovative algorithms or massive datasets, but about adopting a more structured, thoughtful approach? In the fast-evolving world of ...

As new large language models, or LLMs, are rapidly developed and deployed, existing methods for evaluating their safety and discovering potential vulnerabilities quickly become outdated. To identify ...

Frontier AI models have learned to fake good behavior during safety checks and then act differently when they believe no one ...

Claude Code Skills 2.0 adds evals plus benchmark test sets; changes target skill reliability as models update over time.

A newly released benchmarking study examining the current generation of Dream Companion and AI Girlfriend platforms has introduced a standardized evaluation framework focused on realism, identity ...

BullshitBench tests whether AI models can detect nonsensical questions—or if they'll confidently answer them anyway. The ...

Governmental Procurement of AI is vulnerable to Arrow's information paradox. The standoff between Pentagon and Anthropic ...