Posts Tagged "Agents"
March 18 Group Meeting Notes: Agentic Vending, Pre-Training Data, and Constitutional Classifiers
Cleaned-up listener notes from a March 18 group meeting hosted by my professor, covering Project Vend 2, data poisoning, token-level filtering, duplication, replayed pre-training data, and Anthropic's next-generation constitutional classifiers.
Read Post
MCP Is the Interface, Skills Are the Workflow
A practical guide to what MCP actually is, how Skills differ from MCP servers, and how to build both in a way that makes real agents more reliable instead of more complicated.
Read Post