Cosmo Du

Muse Code @Meta

[Cosmo Du @Answeror]

@phanindra_ai @morganlinton right now the subscriptions are limited to muse code
we've tuned muse code for muse models
would love to learn anything missing that's keeping you on pi

[Cosmo Du @Answeror]

@teortaxesTex you may want to try max reasoning effort in muse code
it completely replaced my use of opus4.8 and gpt5.6

[Zhiqing Sun @EdwardSun0909]

Which model is benchmaxxing?

If a model is good across different measurements, maybe it’s just good

[DHH @dhh]

Got muse cli hooked up for both default agent action and lazy-loading. Come give it a try, @finkd 🙏 https://t.co/VOPInLga7S

[DHH @dhh]

If you're not YOLO'ing, are you even vibing??

[Cosmo Du @Answeror]

@phanindra_ai @morganlinton hi Phanindra, max in available in standard tier but not contributor tier. could you select muse-spark-1.3 in /models and then check if /effort shows max?

[DHH @dhh]

I had Muse Code convert a TanStack version of our new site to Astro. It did a flawless job. And all I managed to spend was 20 cents!! I think maybe this token stash from @finkd and @AIatMeta is going to last longer than the sun has gas left to shine 🌅

[Vals AI @ValsAI]

Meta Muse Spark 1.3 (Max) matches the performance of Fable 5 and GPT 5.6 Sol on the Vals Index, at 4x - 8x cheaper.

[Cosmo Du @Answeror]

@galin_denev looking into it

[Cosmo Du @Answeror]

muse spark 1.3 max fixed a muse code issue overnight

[Cosmo Du @Answeror]

heading back home and leaving muse code developing itself tonight

[Cosmo Du @Answeror]

muse code tips #1: ephemeral worktrees

muse -w creates an isolated worktree under .muse/worktrees/
auto-removed when safe, retained with a reason if not

[Cosmo Du @Answeror]

heading back home and leaving muse code developing itself tonight

[Alexandr Wang @alexandr_wang]

1/ we just publicly released Muse Spark 1.3 max!

we see significantly stronger coding and agentic performance on muse spark 1.3 max, so would strongly recommend trying it out even if you've already tried muse spark 1.3 high or muse spark 1.3 xhigh.

[Cosmo Du @Answeror]

@cherry_mx_reds Thanks for trying out Muse Spark 1.3!
Would love to hear your use cases where DeepSeek Harness does a better job.

[Cosmo Du @Answeror]

100X cheaper frontier model in Muse Code!

[Alexandr Wang @alexandr_wang]

underrated result of muse spark 1.3

try it out with muse code:

curl -fsSL https://t.co/TFXsXfJKW8 | bash

[Alexandr Wang @alexandr_wang]

underrated result of muse spark 1.3

try it out with muse code:

curl -fsSL https://t.co/TFXsXfJKW8 | bash