介绍 `gpt-oss Pro Mode`！ 基本上是 o3 Pro，但适用于新的 OpenAI 开源模型 :) Pro Mode 将多达 10 个实例的新的 OpenAI GPT-OSS 模型串联在一起，使其能够产生比单个实例更好的答案！ 开源，链接在这里：

在 Macbook M4 Max 上 gpt-oss 120b: 48 个 token/秒 高速 35 个 token/秒 正常 23 个 token/秒 低功耗 输出非常不错，新的选择模型

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.

openai gpt-oss 聊天应用程序，带有 thinking-ui（100% 本地）:

自从OpenAI发布gpt-oss，完全开源的模型，已经过去了19个多小时。 人们已经开始用它展现出疯狂的创造力和成果。 10个疯狂的例子：