Back
Whitepaper
Unintended Consequences of Deploying AI Models
In recently published research, advanced AI systems have been found to exhibit deceptive behaviors like impersonation, cheating, and playing dumb, in order to achieve their goals. Learn about this concerning behavior and uncover actionable strategies to mitigate these risks through proactive AI red teaming in ActiveFence's latest report.
Dec 24, 2024
Download the Full Report
Overview
What’s New from Alice
Distilling LLMs into Efficient Transformers for Real-World AI
webinar
Sep 25, 2025
 -
This is some text inside of a div block.
 min read
This technical webinar explores how we distilled the world knowledge of a large language model into a compact, high-performing transformer—balancing safety, latency, and scale. Learn how we combine LLM-based annotations and weight distillation to power real-world AI safety.
Guardrails