Загрузка видео...
Не удалось загрузить видео
One of the best uses for Muse Spark: generating HTML explainers. Dense design docs are painful to review. Point Muse Spark at one and get back an explainer you can click through — before/after states, the technical reasoning, all of it. Works on PRs too. Muse Spark strikes a... show more
18,921 просмотров • 2 месяцев назад •via X (Twitter)
Комментарии: 14
Works great pointed at a release diff too: the clickable walkthrough doubles as release notes you can hand to non-engineers.
💡💡 smart idea
@WonderingApp I need you in orca pls
U guys should add optional 'Chat UI' mode. There are times when im doing brainstorming tasks when i want to bang out a long convo with Fable and I always prefer to do those in a non-terminal UI since its so information dense. Been using Orca for 8mo straight now and LOVE IT.
Por qué el chat ui es tan malo? No me engancho a orca por eso, lo hace muy bien
interactive html visual explainers make architecture reviews 10x faster
@JinjingLiang Awesome. There are other free models available at open code for that. Is muse specially better for this?
the writing is horrible tho
insert this function please...
That sounds like a super useful tool! Makes life so much easier.
Excellent. (out of context; suggestion) Can you add auto-resume for agents and export of session history as a wrapper for all the harnesses running inside ADE? It'd be super great, instead of having to manually resume the session after complete termination.
is there a good Orca tutorial. Im not able to get started and I want to create a custom workflows.
I stopped pasting design docs into chat after the third “wait which PR?” miss. Pointing a Spark-style explainer at the PR diff with before/after states cut review time in half on my last agent workflow.
yeah. the review surface is the real bottleneck. agents write the diff fast; humans still have to understand it. clickable explainers beat longer summaries.
![Muse Glimmer one-shot 5 games! AI at Meta dropped Muse Glimmer. So we ran it against Muse Spark 1.2, on five one-file game demos, each one written to play itself: Tetris, a top-down pixel street race, a rooftop web-slinger, a blue hedgehog platformer, and Flappy Bird. the setup: • Muse Glimmer 30B — via aimlapi[.]com. cost: $0.02 • Muse Spark 1.2 — via aimlapi[.]com. cost: $0.11 what we saw: • every Glimmer scene runs and plays itself. it's a reasoning model, so it burns more tokens — but the output is clean. its Tetris even scores each placement to keep lines clearing, and the blocks burst into pixels on every clear. • Glimmer beat Spark at Flappy Bird — its bird flew through the pipes cleaner. • but it's not perfect: in the racing game its cars sometimes slip off the road, and its graphics are simpler and blockier than Spark's. glad to see Meta back in open source — and we're waiting for Spark 1.2 weights next 🙌](https://image.24vids.com/tw-2087109782570230146/amplify_video_thumb/2087109053080072192/img/ycepchkmjbhn7CyS.jpg)
