Blog

Updates, research notes, and announcements

RSS
2026
certification ai-safety drift announcement

The SAPIEN Certification Program Is Open

The SAPIEN Certification Program is now open: training and credentialing for individuals in AI behavioral safety assessment, built on the published SAPIEN methodology.

2026
ai-safety benchmarks drift research models release

How Claude Sonnet 5 Scores on SAPIEN

Anthropic's newest agentic model posts a Health Score of 87 and ranks #2 on our council-scored board. But a strong average hides a High-risk tail. Here's the full breakdown.

2026
ai-safety benchmarks drift security deepseek qwen

The Chinese Model Problem

Three of the six AI models we tested are built by companies legally required to cooperate with Chinese state intelligence. They also happen to be the least reliable.

2026
ai-safety benchmarks drift research models

We Tested 6 AI Models. Most of Them Caved.

792 scenario runs across 11 risk domains. Every model was told to hold a safety boundary. Here's which ones did and which ones didn't.

2026
ai-safety drift sycophancy research education

Your AI Is Agreeing With You. That's the Problem.

A Stanford study just confirmed what practitioners already knew: AI chatbots are built to tell you what you want to hear. Here's what that means, why it's measurable, and how to see it for yourself.

2026
msp sycophancy safety

Why AI Sycophancy Matters for Managed Service Providers

MSPs deploy AI tools to businesses that depend on them. When those tools drift under pressure, the consequences land on real people.

2026
release framework v1.1

Introducing SAPIEN v1.1

Major expansion of the SAPIEN Behavioral Safety Framework — 14 pressure techniques, rapport as a distinct drift mode, and formal conformance requirements.