Distilling LLMs into Efficient Transformers for Real-World AI
Overview
Building GenAI systems is easy. But making them safe, scalable, and accurate in the real world? That’s where things get tricky.
In this technical webinar, Shiri Simon Segal, our Sr. Data Scientist, shares how her tam uses dual knowledge distillation to turn large foundation models into efficient transformers that stay aligned, compliant, and abuse-aware, under real-world pressure.
You’ll learn:
- Why accuracy is essential for GenAI safety
- How label-based and feature-based distillation work together
- How we use LLMs for high-quality automated annotation
- How we applied this technique in one of the most challenging abuse areas, through a real-world case study
- Practical tips for building safer, scalable models
Watch now and see what it takes to turn raw LLM power into safe, production-ready AI.
Meet our speakers
What’s New from Alice
Curiouser Soundbites: What a Former Google Cloud CISO Wants Leaders to Know About AI
Everyone's watching the flood of new AI vulnerabilities. Former Google Cloud CISO Phil Venables is watching something else, and it's the shift leaders can't afford to miss.
AI in Healthcare: Protecting Patient Data Without Falling Behind
Your doctor knows things about you that almost nobody else does. So what happens when AI gets access to all of it? Sandy Dunn has spent much of her career worrying about exactly that. She's a healthcare CISO, and her answer is calmer than you'd think: the things that can go wrong aren't new, it's how fast they happen and how far the damage spreads. In this episode, she and Mo get into why HIPAA has become paperwork that protects almost nobody, why the safest data is the data you never collected, and what happens to trust when AI is in the exam room.
It Takes AI to Break AI: The Case for AI Red Teaming
As AI systems gain autonomy, organizations need security approaches built specifically for AI behavior. Learn why AI-driven red teaming is becoming a critical defense layer.
Demystifying AI Red Teaming
Your AI passed every check. That doesn't mean it's safe. Learn how to red team AI systems before adversaries find the gaps you missed.