Llama Guard
An open-source Meta tool for filtering and moderating inputs and outputs of language models for safety.
As defined in Mark Zuckerberg — AI will write most Meta code in 18 months
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “Llama Guard” →
- A real risk of using a model tied to another government is that it could embed vulnerabilities in code that the country's intelligence organizations could later exploit — you could wake up to systems that model secured being vulnerable in a way that country knows about and you don't, or it could activate a vulnerability at some point.Mark Zuckerberg — AI will write most Meta code in 18 months
- Distilling language models is fraught because of embedded values, but for reasoning models limited to verifiable domains you can distill quite securely by combining code cleanliness and security filters, tools like Llama Guard and Code Shield, and extensive red teaming to check the model isn't doing anything unwanted after distillation.Mark Zuckerberg — AI will write most Meta code in 18 months