Introducing `gpt-oss Pro Mode`! Basically o3 Pro, but for the new OpenAI open source models :) Pro Mode chains together up to 10 instances of the new OpenAI GPT-OSS model, enabling it to produce a better answer than one instance alone could create! Open source, link here:

No Macbook M4 Max GPT-OSS 120B: 48 tok/s de altura 35 tok/s normal 23 tok/s baixa potência Saídas muito boas, novo modelo de escolha

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.

Construí uma equipe de agentes de IA imobiliária com multiagentes usando gpt-OSS e Firecrawl. Possui 3 agentes de IA trabalhando juntos como uma equipe: 1. Agente de Busca de Imóveis 2. Agente de Análise de Mercado 3. Agente de Avaliação de Imóveis 100% Opensource com tutorial passo a passo.

Aplicativo de bate-papo OpenAI GPT-OSS com Thinking-UI (100% local):

Faz apenas pouco mais de 19 horas desde que a OpenAI lançou o gpt-oss, modelo totalmente de código aberto. E as pessoas já estão ficando loucamente criativas e resultados com isso. 10 exemplos selvagens: