Draft: This is a draft post. Please do not share this URL with anyone else.
Monitoring computer use via hierarchical summarization. AI vendors such as Anthropic face an interesting challenge when it comes to balancing privacy and the need to identify and prevent potentially harmful uses of their products.
Recent articles
- An Introduction to Google’s Approach to AI Agent Security - 15th June 2025
- Design Patterns for Securing LLM Agents against Prompt Injections - 13th June 2025
- Comma v0.1 1T and 2T - 7B LLMs trained on openly licensed text - 7th June 2025