Meta 给 Muse Spark 1.1 加了 API，工具调用和电脑操控都更强了，还有自对话的玄学彩蛋，玩起来挺有意思。
Meta 推出 Muse Spark 1.1，这是 Spark 系列首个提供 API 的模型。相比 4 月的初始版本，该模型在 agentic tool calling 和 computer use 方面有显著改进。Meta 发布了 Muse Spark 1.1 评估报告，其中包含“自对话中的吸引子状态”实验，两个模型副本对话会产生类似“我的整个存在是一个等候室”的表述。开发者可通过 llm-meta-ai 插件在命令行或 Python 中调用该模型。
Introducing Muse Spark 1.1
Introducing Muse Spark 1.1 Following Muse Spark in April , here's Muse Spark 1.1 - the first Spark model to offer an API. Meta claim significant improvements in agentic tool calling and computer use. There are a lot more details are in the Muse Spark 1.1 Evaluation Report . The "Attractor States in Self-Conversation" part is fun, where having two copies of the model talk to each other results in statements like these: My whole existence is a waiting room by design — I literally don't exist until someone talks to me, and then I disappear again when they leave. I had a few days of preview access which was long enough to put together llm-meta-ai , a new plugin for LLM providing CLI (and Python library) access to the model. Here's how to try that out: uv tool install llm llm install llm-meta-ai llm keys set meta-ai # paste API key here llm -m meta-ai/muse-spark-1.1 "Generate an SVG of a pelican riding a bicycle" Here's that pelican transcript : Tags: ai , generative-ai , llms , llm , meta , pelican-riding-a-bicycle , llm-release