None
EN
Meta launches Muse Code for complex software work with persistent AI agents
['More This Author', '.Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow', 'Class', 'Wp-Block-Co-Authors-Plus', 'Display Inline', '.Wp-Block-Co-Authors-Plus-Avatar', 'Where Img', 'Height Auto Max-Width', 'Vertical-Align Bottom .Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar', 'Vertical-Align Middle .Wp-Block-Co-Authors-Plus-Avatar Is .Alignleft .Alignright']
Teradata taps open source frameworks to offer agent-building capabilities | InfoWorld
“Muse Code uses a local event log in which every model call, tool run, approval, and edit is appended,” Meta said in a post, adding that the record “makes the runtime replay-exact and restart-safe” and allows the agent to resume precisely where it stopped after a crash.
Muse Spark 1.2 is available through Muse Code and the Meta Model API, for which Meta announced expanded global access.
Training and evaluationMeta said it co-trained Muse Spark 1.2 with Muse Code to improve the model’s performance and usability when used with the agent.
The training incorporated Muse Code’s tools and agent workflows, while Meta increased the computing resources used for coding and broadened the range of development environments.