# Muse Code Co-Trains the Harness — Spark 1.2 Alone Is Incomplete

Times of AI Desk · 2026-08-05 · Models

[https://timesof.ai/2026/08/meta-muse-code-spark-1-2](https://timesof.ai/2026/08/meta-muse-code-spark-1-2)

> Meta shipped Muse Code beta, a terminal coding agent with persistent background subagents and a replay-exact event log, powered by Muse Spark 1.2. Lab coding benches lead the post.

**Corrected October 14, 2026:** Removed an undated Arena Elo figure and unverified Artificial Analysis scores and comparisons; the summary now says lab coding benchmarks lead the post.

Meta is no longer only shipping chat/multimodal Muse — it is competing in the **terminal agent** market where Anthropic (Claude Code), OpenAI (Codex / ChatGPT Work), and Cursor-class tools already live. Co-training model + harness is the real product thesis: **Spark 1.2 without Muse Code is incomplete**.

**Meta** shipped **Muse Code (beta)** — a **terminal coding agent** — powered by **Muse Spark 1.2**, the newest Muse Spark tier. Install path: `curl -fsSL https://dev.meta.ai/install.sh | bash` (macOS/Linux). Muse Spark 1.2 is available in **Muse Code** and **Meta Model API** with expanded global access. The stack targets **long-horizon** multi-file / whole-repo engineering.

## What shipped

| Piece | Detail (Meta primary) |
|-------|------------------------|
| **Muse Code** | Terminal agent: plan, implement, validate multi-file changes across large repos |
| **Background agents** | Persistent specialized subagents across a session (not one-shot spawns) |
| **Runtime** | Local **event log** of model calls, tools, approvals, edits — **replay-exact**, restart-safe |
| **Bundled skills** | `/plan` (approval-gated plan), `/grill` (stress-test plan), `/goal` (objective completion) |
| **Muse Spark 1.2** | Coding-focused update to **1.1**: more coding train compute, environment diversity; co-trained with Muse Code harness |
| **Long-horizon** | Whole-repo generation, large projects, auto-research; planning + goal conditioning + context compaction |
| **Case study** | GPU **kernel optimization** over **1,000+** tool calls (up to **24 hours**) on Hopper KDA/MLA kernels |

Meta frames 1.2 as an interim step “toward the frontier, with larger and much more capable models on the way.”

## Claims vs checks

**Lab-reported:** Meta publishes Terminal-Bench 2.1, DeepSWE 1.1, and internal coding-bench charts on the launch post (see methodology report linked from the blog). Kernel case studies claim progressive speedups vs. baseline Triton/PyTorch references under tool-call budgets.

**Independent (as available near launch):**

- **Artificial Analysis**: no dated 1.2-specific Intelligence Index result was checked for this article.

## Limits

- If Arena votes for 1.2 are thin in the first days, rank is not settled.
- 1.2-specific full AA Index may lag the launch post.
- API pricing/rate limits and “larger models on the way” remain open.

## Sources

- [Meta AI Research: Introducing Muse Code and Muse Spark 1.2 (August 5, 2026)](https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2)
- [Meta AI Research hub](https://ai.meta.com/research/)
- [Artificial Analysis: Muse Spark model page](https://artificialanalysis.ai/models/muse-spark)
- Times of AI: [Meta Muse Spark 1.1 model and API](https://timesof.ai/2026/07/meta-muse-spark-1-1-model-api) (July 9)