aiqbenchInformații despre AI & calcul cuantic

...

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchProduse AI

Meta AI's release of Muse Code marks a significant advancement in terminal-based coding agents by introducing persistent async background processes that maintain session continuity without redundant task spawning. The underlying Muse Spark 1.2 model is specifically co-trained on long-horizon, repository-scale workloads to handle complex engineering tasks like kernel optimization and multi-day bug triage with improved latency management. This development shifts the focus from isolated code generation toward sustained, stateful agent loops capable of managing large software repositories autonomously.

Surse care acoperăMarkTechPost, Latent Space, Viakoo, Hugging Face

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model

MarkTechPost5 august 20265 min de cititArticolul și perspectiva sunt în engleză.

Meta Superintelligence Labs has released Muse Code, a terminal coding agent in beta, powered by the new Muse Spark 1.2 model. Muse Code plans changes, writes code, and validates results across large repositories. Async background agents stay active for the whole session instead of spawning per task. A local append-only event log makes the runtime replay-exact and restart-safe after a crash. Muse Spark 1.2 was co-trained with the harness and trained on long-horizon, repository-scale work. The post Meta AI Releases Muse Code (Beta): A Terminal Coding Agent Powered by the New Muse Spark 1.2 Model appeared first on MarkTechPost.

Meta AI has released Muse Code, a terminal coding agent in beta, powered by its new Muse Spark 1.2 model. Meta positions the pair as its next step toward the frontier, with larger models on the way. Muse Code targets complex software engineering across large repositories: it plans changes, writes code, and validates the results. A set of async background agents stays alive for the whole session instead of spawning per task. A local append-only event log records every model call, tool run, approval, and edit, which…

Extras afișat conform termenilor RSS ai publicației · 87 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe MarkTechPost ↗Întreabă despre acest articol