Topic
Vs Code
2 episodes
-
What 50,000 Runs of a 5 Line Eval Taught Us
The VS Code team ran a simple 5-line eval 50,000 times to test AI models' efficiency in completing a basic task: writing a string to a file. The goal was to see how reliably models could finish the work and what kinds of failures show up. The eval, called 'say_hello,' asks the model to add 'HELLO' to a file named 'HELLO.txt.'
-
Giving Agents a Visual Voice: MCP Apps Support in VS Code
This podcast episode explores the new MCP Apps feature in VS Code, which empowers AI coding agents with interactive visual capabilities. This innovation transforms the way developers collaborate with AI tools, enhancing productivity and problem-solving. Through real-world applications and examples, hosts discuss the implications and potential use cases of this exciting feature.