# meta-muse-code-muse-spark-1-2-2026-08-05

## Veille

Announcement from **Meta AI Research** published on **August 5, 2026** (stated reading time: 4 minutes, no individual byline): **Muse Code** in beta, *« a terminal coding agent »*, and the model that powers it, **Muse Spark 1.2**. Meta itself frames the launch: *« This marks our next step toward the frontier, with larger and much more capable models on the way. »* **Three architectural elements on the harness side.** **Asynchronous background agents** that *« remain active throughout each session, rather than being spawned for individual tasks »*, avoiding redundant information gathering and reducing the need for steering. A **local event log** where *« every model call, tool run, approval, and edit is appended »*, making the runtime a system that is *« replay-exact and restart-safe »*, able to resume exactly where it left off after a crash. And **three skills shipped out of the box**: `/plan` (turns a task into a plan submitted for approval), **`/grill`** (stress-tests the plan *« until it holds up »*), and `/goal`. **On the model side**, Meta claims **model-harness co-training** (*« to maximize harness compatibility »*, with harness trajectories sampled via rejection sampling and recipe optimizations for goals, compaction, and sub-agents), **long-horizon** training (whole-repo generation, end-to-end projects, self-research, with planning, goal conditioning, and context compaction), and a **self-improvement loop** where Muse Spark 1.1 generates the environments and instruction templates and then grades candidate solutions, producing a training set for the 1.2. **What the published charts show**, without the text commenting on it: the four comparisons — Terminal-Bench 2.1, DeepSWE 1.1, an internal Meta benchmark, and the GPU kernel optimization case study — place **Muse Spark 1.2 behind Opus 5 in all four cases**, including on Meta's own proprietary benchmark (70.6% versus 79.4%) and on the case study, where the model finishes fourth out of six (+68.7% versus +74.0%). **A reading caution on the version gain**: on the two public benchmarks, 1.1 is measured with `mini-swe-agent` and 1.2 with Muse Code, so the 6.7-point gap conflates model and harness. On the internal benchmark, the only comparison where no harness is mentioned, the 1.1 → 1.2 gap drops to **2.3 points**.

## Titre Article

Introducing Muse Code and Muse Spark 1.2

## Date

2026-08-05

## URL

https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2

## Keywords

Meta AI Research, Muse Code, Muse Spark 1.2, terminal coding agent, beta, harness, asynchronous background agents, persistent sub-agents, redundant information gathering, event log, event log, replay-exact, restart-safe, crash recovery, long-running tasks, shipped skills, approved plan, grill, goal, model-harness co-training, rejection sampling, harness trajectories, harness compatibility, long-horizon, whole-repo generation, self-research, goal conditioning, context compaction, self-improvement, environment generation, solution grading, Terminal-Bench 2.1, DeepSWE 1.1, internal benchmark, Opus 5, Claude Code, GPT 5.6 Terra, GPT 5.6 Sol, Codex, Grok 4.5, Gemini 3.6 Flash, Antigravity CLI, mini-swe-agent, GPU kernel optimization, Triton, KDA, MLA, NVIDIA Hopper, cumulative tool calls, speedup vs baseline, FLA, kernel fusion, tiling, Meta Model API, lock-in through optimization

## Authors

**Meta AI Research** — publication institutionnelle sans auteur nommé, sur `research.meta.ai`. Le billet renvoie à un **rapport** pour la méthodologie d'évaluation, non repris ici.

**Positionnement à connaître** : Meta arrive sur le terrain de l'agent de codage en terminal **après** Claude Code, Codex, Gemini CLI, Grok Build et Antigravity CLI, et le dit — *« our next step toward the frontier »*. L'annonce couple un **produit** (Muse Code, distribué par `curl … | bash`) et un **modèle** (Muse Spark 1.2, disponible dans Muse Code et dans **Meta Model API** avec *« expanded global access »*), les deux ayant été entraînés ensemble.

## Ton

**Profile**: a research-lab product announcement, short format, sober technical register. No hyperbole, no claim of superiority, no superlatives — which is **unusual for a launch** and is itself informative.

**Style**: the text proceeds by **describing mechanisms**, section by section, each one a single paragraph naming a specific engineering decision — sub-agent persistence, the event log, co-training, compaction. There is no customer case, no executive quote, no productivity promise. The only narrative demonstration is a vignette: a user drops a house-tour video in `mp4` into the terminal, Muse Code interprets it, and produces a short-term rental booking page.

**The most notable trait is the modesty of the framing**, set out as early as the second sentence: *« This marks our next step toward the frontier, with larger and much more capable models on the way. »* Meta announces a milestone and signals that the best is yet to come. The conclusion repeats the same posture: *« We have a lot on the horizon, including new harness features and more powerful models. »*

**This modesty checks out in the charts**, and that's what makes the announcement distinctive: Meta publishes four comparisons in which it never wins. Few launches are willing to show a competitor in the lead on their own page — even less so on their **own internal benchmark**.

**Marker phrases**: *« our next step toward the frontier »*, *« rather than being spawned for individual tasks »*, *« replay-exact and restart-safe »*, *« /grill stress-tests that plan until it holds up »*, *« to maximize harness compatibility »*.

## Pense-betes

- **Date / source**: **August 5, 2026**, Meta AI Research, unsigned announcement. **Muse Code** (beta), a terminal coding agent installed via `curl -fsSL https://dev.meta.ai/install.sh | bash` on macOS and Linux, and **Muse Spark 1.2**, available in Muse Code and in Meta Model API.
- **Key framing**: no figures appear in the text — the four comparisons are raster images. The values below were read visually off the PNGs. ### The four comparisons | Comparison | Winner | Muse Spark 1.2 | Rank | |---|---|---|---| | Terminal-Bench 2.1 | Opus 5 + Claude Code — **86.7%** | 82.9% | 2nd / 6 | | DeepSWE 1.1 | Opus 5 + Claude Code — **65.0%** | 59.3% | 3rd / 6 | | **Meta Internal Coding Bench** | Opus 5 — **79.4%** | 70.6% | 2nd / 5 | | KDA case study (speedup) | Opus 5 — **+74.0%** | +68.7% | **4th / 6** | On its own proprietary benchmark, Meta sits 8.8 points behind Opus 5; on the case study chosen as a showcase, it also falls behind GPT 5.6 Sol (+71.2%) and behind Anthropic's previous generation, Opus 4.8 (+69.6%). ### The model gain is smaller than displayed On Terminal-Bench and DeepSWE, 1.1 is evaluated with **`mini-swe-agent`** and 1.2 with **Muse Code**: the displayed gap (76.2 → 82.9, i.e. **+6.7 points**) conflates model progress and harness progress. On the internal benchmark, the only table where no harness is indicated, the 1.1 → 1.2 gap drops to **68.3 → 70.6, i.e. +2.3 points**. None of these comparisons is model-against-model: they are **model + harness** pairs, each model measured with its own lab's harness. This empirically validates, three weeks apart, the mechanism described by [[mozilla-state-of-open-source-ai-2026-07]] — *« a harness tuned tightly to one lab's weights becomes a fitted component of that lab's product… Lock-in arrives as a side effect of optimization »* — Meta explicitly stating it co-trained the model with the harness *« to maximize harness compatibility »*. ### The event log *« A local event log in which every model call, tool run, approval, and edit is appended »*, a single source of truth making the runtime *« replay-exact and restart-safe »*: after a crash, the agent resumes exactly where it left off, which enables long-running tasks. A direct convergence with the run manifest and the `run resume` command of [[skill-gibbs-hyperresearch-2026-08-03]]. Two independent teams arrive at the same design: context does not survive, an on-disk log does. ### Persistent background agents Instead of being spawned for a task and then destroyed, they *« remain active throughout each session »*, which avoids *« redundant information gathering »*, lets them decide for themselves when to escalate to the main agent, and reduces *« latency and the need for steering »*. Worth setting against the opposite observation from [[lassiege-usine-logicielle-heure-ia-2026-07-28]] on disposable sub-agents (*« I use them less and less »*): two opposite answers to the same problem — delegate less, or delegate to agents that no longer die. ### The three shipped skills `/plan` (a plan **submitted for approval**), **`/grill`** (*« stress-tests that plan until it holds up »*), `/goal`. The loop described is **plan → challenge → execution** with a human gate at the first step. `/grill` picks up the function of a community skill already documented: a pattern born in the community arrives pre-installed at a frontier lab. ### Self-improvement, read precisely *« We also used Muse Spark 1.1 to generate challenging coding environments and instruction-following templates. The model then graded candidate solutions… producing a scalable training dataset for Muse Spark 1.2. »* It is **1.1** that generates the environments and does the grading, with 1.2 being the product of that dataset — the subject of *« the model »* is ambiguous, and some coverage has read it as 1.2. A distillation loop of one generation on itself, whose known limitation is that it can only teach what the previous generation already knows how to evaluate. ### GPU kernel case study: the protocol is worth more than the result Iterative optimization over **more than 1,000 cumulative tool calls, up to 24 hours**, on the **KDA** and **MLA** kernels for NVIDIA Hopper GPUs; the model writes, compiles, profiles, and improves. A notable constraint: *« Models were prohibited from importing third-party kernel libraries such as FLA directly »* — the algorithm had to be reimplemented in Triton, not wrapped around an existing implementation. This is what makes the test honest. On KDA: a block-parallel preparation kernel plus a sequential inter-block scan, with the cumulative decay re-centered at the block midpoint. On MLA: a two-kernel Triton pipeline reusing the shared KV latent as both K and V, measured at batch size 1, 64 heads, sequence length 8,192, latent dimension 512. **KDA is Kimi's linear attention**: Meta is thus having its agent optimize the kernel of a competing open-weights architecture. ### Three methodological caveats on the charts 1. **No figures in the text**: raster images with no text data and no numeric accessibility label. An aggregator, or an agent reading the page, sees no results at all. 2. **The KDA chart's y-axis is non-linear**, which Meta discloses honestly (*« Axis Spaced Linearly In X »*, tick marks at 0-27-43-53-60-65-69-72-75%). The scale stretches the upper range and visually inflates the gaps between top models — to Meta's disadvantage. 3. **The compared configurations are not uniform**: `max` for Opus 5 and GPT 5.6 Terra, `high` for Grok 4.5 and Gemini 3.6 Flash, nothing for Muse Spark. Grok is absent from the internal benchmark, GPT 5.6 Sol appears only in the case study: the panel's composition changes from one chart to the next. The *« Meta Internal Coding Bench »* is not public and its composition is not described; Meta measures its competitors on it. The fact that it loses there makes the figure more credible than a flattering score, but a proprietary benchmark remains non-reproducible. ### What the announcement does not say No pricing, no usage limits, no model license, no weight openness — a notable break from the Llama tradition, on which the post is silent. Nothing either on supported languages, context size, or confidentiality guarantees for submitted code.

## RésuméDe400mots

Announcement from **Meta AI Research** dated **August 5, 2026**: **Muse Code** in beta, a terminal coding agent, and **Muse Spark 1.2**, the model that powers it. Meta itself frames the launch — *« our next step toward the frontier, with larger and much more capable models on the way »*.

**On the harness side, three decisions.** **Asynchronous background agents** that *« remain active throughout each session, rather than being spawned for individual tasks »*, avoiding redundant information gathering and deciding for themselves when to escalate to the main agent. A **local event log** recording every model call, tool run, approval, and edit, which makes the runtime *« replay-exact and restart-safe »*: after a crash, the agent resumes exactly where it left off. And three **skills shipped out of the box**: `/plan` (a plan submitted for approval), **`/grill`** (stress-tests the plan until it holds up), and `/goal`.

**On the model side**, Meta claims **co-training with the harness** *« to maximize harness compatibility »*, long-horizon training (whole repo, end-to-end projects, self-research, context compaction), and a self-improvement loop where version 1.1 generates the environments and grades the solutions, producing the training set for 1.2.

**The central fact of this announcement is nowhere stated in its text.** The four published comparisons exist only as images, and they place Muse Spark 1.2 **behind Opus 5 in all four cases**: 82.9% versus 86.7% on Terminal-Bench 2.1, 59.3% versus 65.0% on DeepSWE 1.1, **70.6% versus 79.4% on Meta's own internal benchmark**, and +68.7% versus +74.0% on the GPU kernel optimization case study, where the model finishes **fourth out of six**, behind GPT 5.6 Sol and behind Anthropic's previous generation.

**And the model's own gain is smaller than it appears.** On the two public benchmarks, version 1.1 is evaluated with `mini-swe-agent` and 1.2 with Muse Code: the 6.7-point gap conflates model and harness. On the internal benchmark, the only comparison with no harness indicated, it drops to **2.3 points**.

The announcement therefore stands mainly as **empirical confirmation** of a thesis already stated: value is shifting toward the harness, and a harness co-trained with its own weights makes those weights all the more non-interchangeable.

## GrapheDeConnaissance

- Meta AI Research —publie→ Muse Code (TECHNOLOGIE, 0.97)
- Meta AI Research —publie→ Muse Spark 1.2 (TECHNOLOGIE, 0.97)
- Muse Spark 1.2 —est_variante_de→ Muse Spark 1.1 (TECHNOLOGIE, 0.95)
- Muse Code —utilise→ Muse Spark 1.2 (TECHNOLOGIE, 0.96)
- Muse Spark 1.2 —est_basé_sur→ un co-entraînement avec le harnais Muse Code pour maximiser leur compatibilité (AFFIRMATION, 0.95)
- co-entraînement d'un modèle avec son harnais —réduit→ l'interchangeabilité des poids sous-jacents (AFFIRMATION, 0.85)
- journal d'événements local —permet→ de reprendre exactement où l'agent s'est arrêté après un plantage (AFFIRMATION, 0.95)
- agents d'arrière-plan persistants —s_oppose_à→ les sous-agents créés puis détruits pour chaque tâche (AFFIRMATION, 0.94)
- agents d'arrière-plan persistants —réduit→ la collecte d'information redondante et le besoin de pilotage (AFFIRMATION, 0.93)
- Muse Code —utilise→ une skill de mise à l'épreuve du plan avant implémentation (AFFIRMATION, 0.93)
- Muse Spark 1.1 —permet→ de générer les environnements et de noter les solutions ayant servi à entraîner Muse Spark 1.2 (AFFIRMATION, 0.9)
- Opus 5 —surpasse→ Muse Spark 1.2 (TECHNOLOGIE, 0.95)
- Muse Spark 1.2 —mesure→ 82,9 % sur Terminal-Bench 2.1 contre 86,7 % pour Opus 5 avec Claude Code (MESURE, 0.93)
- Muse Spark 1.2 —mesure→ 59,3 % sur DeepSWE 1.1 contre 65,0 % pour Opus 5 et 64,8 % pour GPT 5.6 Terra (MESURE, 0.93)
- Muse Spark 1.2 —mesure→ 70,6 % sur le benchmark interne de Meta contre 79,4 % pour Opus 5 (MESURE, 0.92)
- Muse Spark 1.2 —mesure→ une accélération de noyau KDA de +68,7 %, quatrième derrière Opus 5, GPT 5.6 Sol et Opus 4.8 (MESURE, 0.92)
- comparaison de paires modèle et harnais —s_oppose_à→ une comparaison de modèles isolés, les deux benchmarks publics évaluant chaque modèle avec le harnais de son laboratoire (AFFIRMATION, 0.9)
- gain entre versions —mesure→ 2,3 points sur le seul comparatif sans harnais indiqué, contre 6,7 points sur les comparatifs avec harnais (MESURE, 0.88)
- Muse Code —s_applique_à→ l'optimisation itérative de noyaux GPU sur plus de 1 000 appels d'outils et jusqu'à 24 heures (AFFIRMATION, 0.93)
- interdiction d'importer une bibliothèque de noyaux tierce —permet→ de tester la réimplémentation d'un algorithme plutôt que l'enveloppement d'une implémentation existante (AFFIRMATION, 0.92)
- Meta AI Research —affirme_que→ ce lancement est une étape vers la frontière, des modèles plus grands et plus capables étant à venir (CITATION, 0.95)
- benchmarks publiés uniquement en image —s_oppose_à→ la lisibilité des résultats par un agrégateur ou un agent lisant la page (AFFIRMATION, 0.88)

---
Canonical: https://www.thekb.eu/en/fiches/meta-muse-code-muse-spark-1-2-2026-08-05/