正在加载视频...

视频加载失败

Evals now supports tool use. 🛠️ You can now use tools and Structured Outputs when completing eval runs, and evaluate tool calls based on the arguments passed and responses returned. This supports tools that are OpenAI-hosted, MCP, and non-hosted. Read more in our guides below.

65,080 次观看 • 1 年前 •via X (Twitter)

11 条评论

OpenAI Developers 的头像
OpenAI Developers1 年前

Web Search evaluation:

OpenAI Developers 的头像
OpenAI Developers1 年前

Tools evaluation:

OpenAI Developers 的头像
OpenAI Developers1 年前

Structured Outputs evaluation:

OpenAI Developers 的头像
OpenAI Developers1 年前

MCP evaluation:

Matt Figdore 的头像
Matt Figdore2 年前

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Opulent Byte 的头像
Opulent Byte1 年前

When o3 pro? 🥲🫠

Brij Singh 的头像
Brij Singh1 年前

this is good!

Cliffinkent 🇬🇧 的头像
Cliffinkent 🇬🇧1 年前

You keep building and shipping!

Prashant 的头像
Prashant1 年前

This just makes running evals so much easier. Thank you

Vishal 的头像
Vishal1 年前

Tool support in Evals makes testing AI tools easier and improves accuracy.

Henkjan de Krijger 的头像
Henkjan de Krijger1 年前

Does relying on eval tools hinder critical thinking in AI systems?

相关视频