Steering Vectors: Runtime Behavior Control for LLMs
How to extract behavioral directions from language models and apply them at inference time. A practical guide to rotalabs-steer.
Read articleBlog
Technical deep-dives, research updates, and tutorials.
All Posts
Agent-to-Agent Networks: Trust Dynamics and Attack Surfaces in Moltbook
A technical analysis of trust dynamics, emergent behaviors, and security vulnerabilities in Moltbook - the first large-scale agent-to-agent social network....
Introducing the Rotalabs Open Source Ecosystem
We're releasing 12 packages for AI trust, evaluation, and reliability. Available on PyPI and npm, all AGPL-3.0 licensed.
When AI Agents Don't Know What They Don't Know
The security conversation around AI agents is stuck on identity and permissions. The harder problem is whether an agent should...
Multi-Agent Coordination Without Centralized Control
The standard architecture for coordinating autonomous systems assumes a command node. That works until the link goes down. Here's how...
Runtime AI Control for Contested Environments
Prompting is not a control mechanism. When AI operates in kill chains and beyond reliable comms, 'the model usually follows...
MCP is Infrastructure. Trust is the Missing Layer.
The Model Context Protocol connects AI agents to the world. Everyone's focused on securing the connections. But you can authenticate...
The CoT Blind Spot: Why Watching What Models Say Isn't Enough
Chain-of-thought monitoring was supposed to let us supervise AI reasoning. But new research shows models only faithfully report their reasoning...
Memory Poisoning: The Attack Vector Nobody's Ready For
A single compromised agent poisoned 87% of downstream decisions in 4 hours. As AI agents gain persistent memory, attackers are...
Prompt Injection Is Still Unsolved: What the Latest Research Actually Shows
A joint paper from OpenAI, Anthropic, and DeepMind bypassed 12 published defenses. NAACL 2025 broke 8 more. Here's where we...
The Multi-Agent Trust Problem: Why Your AI Agents Can't Verify Each Other
As AI agents collaborate on complex tasks, a critical question emerges: how does Agent A know Agent B isn't compromised,...
Detecting AI Sandbagging with Activation Probes
First empirical demonstration of activation-level sandbagging detection. Linear probes achieve 90-96% accuracy across Mistral, Gemma, and Qwen models. Sandbagging representations...