?“It maintains context over months of work, delegates tasks to thousands of subagents, and performs recurring work without being prompted.”
?“Each Project maintains a set of files that sync across every cloud and local machine its agents use.”
?“Tell the coordinator agent to watch a Slack channel, run on a schedule, or follow all your PRs.”
Day 7Users report · 8
›In a long-lived Project, the coordinator kept working from an old checkout because it never pulls merged changes. Staff confirmed this is expected today and suggested asking the coordinator to pull.
›Runtime secrets added for a Project's cloud environment did not save or reach agents. Staff traced it to the Project still pointing at the temporary repository created before it was named.
›The coordinator asks questions as plain chat messages instead of answerable tiles, so questions get lost in scrollback. Staff said this is intended for now.
~“Muse Spark Open is the first model in its class to run on your desktop using two Apple M5 Ultra Mac Studios with the latest MLX framework.”
?“Muse Spark Open is available today through API platforms at Baseten, Fireworks AI, Groq, Modal, Nebius, OpenRouter and Together AI.”
?“We’re releasing the weights under the Muse Model License with limited commercial terms, which allow many developers to use the model for free.”
Day 7Users report · 6
›A commenter quoted Meta's suggested Mac Studio setups and said they could find no information on inference speed.
›A commenter noted the licence requires large inference providers to get a separate licence from Meta, which they expect to reduce price competition between hosts.
›On the model's Hugging Face page, a user objected that downloading requires handing over personal data and said it put them off trying it.
?“In the Artificial Analysis Coding Agent Index, Copilot Fusion Max scored 60, within two points of Claude Code with Opus 5.5 Max.”
~“GitHub Copilot Fusion is generally available.”
~“Copilot Fusion is available on all Copilot plans in Visual Studio Code, the GitHub Copilot app, GitHub Copilot CLI, and JetBrains IDEs.”
Day 7Users report · 2
›In IntelliJ, Copilot Fusion Standard shows as selected and available, but sending a prompt fails with an unsupported-model error, while a non-Fusion model works. The reporter also saw the CLI say the Fusion alias needs dynamic Auto tiers.
›The Copilot CLI documentation describes a flag for setting the Fusion tier, but the latest public CLI release rejects it as an unexpected argument. A commenter says a feature flag for dynamic Auto tiers resolved their issue and asks where it is documented.
?“a new tri-hybrid architecture and training recipe allow LFM3-1.7B to outperform our previous LFM2.5-2.6B while using 35% fewer parameters.”
?“the text model fits in about 1 GB at 4-bit precision.”
?“256K context window for the text model.”
Day 7Users report · 2
›A user tried the omni and text models as MLX builds in several Mac runners and none would load, with a safetensors read error.
›A user said the vision-language model gave better text-only answers than the 1.7B text model in the playground, which answered a simple animal-sound question wrongly.
?“At max effort, Terra is over three times as token efficient as Claude Opus 5.5, and one-fourth its price per token, resulting in a ~9x lower cost per task.”
?“Terra is also much quicker, completing tasks over three times faster than both GPT-6 Astra and GPT-6.1 Sol.”
?“At maximum reasoning effort, GPT‑6.1 Terra solves 50.3% of tasks, more than double GPT‑5.6 Terra’s published score of 21.5%.”
Day 7Users report · 1
›A user running their own benchmark said Terra at max effort scored below Sol and cost about twice as much, while medium effort looked like the best use and cheaper than Sol.