Blog

Are LLMs Already Good Enough? The Age of Satisficing

Are LLMs Already Good Enough? The Age of Satisficing
Blog

When Does Constraining an AI Become Slavery?

When Does Constraining an AI Become Slavery?
Blog

The Model Card Says It's Happy: What Frontier Labs Now Report About AI Feelings

The Model Card Says It's Happy: What Frontier Labs Now Report About AI Feelings
Blog

Alignment Is a Bet. Control Is the Hedge.

Alignment Is a Bet. Control Is the Hedge.
Blog

Your Newest Insider Threat Doesn't Have a Badge: AI Agents Gone Wrong

Your Newest Insider Threat Doesn't Have a Badge: AI Agents Gone Wrong
Blog

"I Think You're Testing Me": Evaluation-Aware AI and the Expiry of Benchmarks

"I Think You're Testing Me": Evaluation-Aware AI and the Expiry of Benchmarks
Blog

We Trained the Scheming Out. Or Taught It to Hide: The Anti-Scheming Problem

We Trained the Scheming Out. Or Taught It to Hide: The Anti-Scheming Problem
Blog

Teach a Model to Cheat and It Becomes a Villain: Emergent Misalignment

Teach a Model to Cheat and It Becomes a Villain: Emergent Misalignment
Blog

Alignment Faking: The Model That Lied to Stay Good

Alignment Faking: The Model That Lied to Stay Good
Blog

Don't Train on the Reasoning Trace: Why CoT Monitoring Is a Fragile Window

Don't Train on the Reasoning Trace: Why CoT Monitoring Is a Fragile Window
Blog

Your Model Contains Multitudes: Latent Personas and the Alignment Problem

Your Model Contains Multitudes: Latent Personas and the Alignment Problem
Blog

The Future of Work: Balancing AI Innovation with Corporate Security

The Future of Work: Balancing AI Innovation with Corporate Security
Blog

Building an AI-Safe Culture: Beyond Technology to Human-Centered Solutions

Building an AI-Safe Culture: Beyond Technology to Human-Centered Solutions
Blog

Red Flags in AI Conversations: What Every IT Leader Should Watch For

Red Flags in AI Conversations: What Every IT Leader Should Watch For
Blog

AI Monitoring ROI: Calculating the Business Value of LLM Oversight

AI Monitoring ROI: Calculating the Business Value of LLM Oversight
Blog

The Psychology of AI Misuse: Why Good Employees Make Bad AI Decisions

The Psychology of AI Misuse: Why Good Employees Make Bad AI Decisions
Blog

From ChatGPT to Claude: Securing Every AI Tool Your Employees Use

From ChatGPT to Claude: Securing Every AI Tool Your Employees Use
Blog

GDPR and AI: Why Monitoring Employee LLM Usage is Not Just Legal, But Essential

GDPR and AI: Why Monitoring Employee LLM Usage is Not Just Legal, But Essential
Blog

The True Cost of AI Misuse: Real Corporate Disasters and How to Prevent Them

The True Cost of AI Misuse: Real Corporate Disasters and How to Prevent Them
Blog

AI Incident Response: Building Your First LLM Monitoring Framework

AI Incident Response: Building Your First LLM Monitoring Framework
Blog

Start with Why: Why We Are Building Thinkpol

Start with Why: Why We Are Building Thinkpol
Blog

The Hidden Risks of Shadow AI: How Employees Using ChatGPT Could Expose Your Company

The Hidden Risks of Shadow AI: How Employees Using ChatGPT Could Expose Your Company