Very keen to try this after using Claude Code over the last few months.
Should I just point Claude Code to Muse Spark endpoint (because I'm familiar with Code)? What do people think of Muse Code or other coding agent harnesses?
Muse Spark 1.3
241–250 of 475 posts
Re: Muse Spark 1.3
#242How do people actually use this? Do they use it through some sort of subscription plan, or via OpenRouter?
Re: Muse Spark 1.3
#243Very keen to try this after using Claude Code over the last few months. Should I just point Claude Code to Muse Spark endpoint (because I'm familiar with Code)? What do people think of Muse Code or other coding agent harnesses?
Just try opencode, it comes with 1.3 contributor free.
Re: Muse Spark 1.3
#244Practically free for "contributors" at 0.2 usd/mtok. That's going to be hard to say no to for hobbyists.
Price segmentation at its finest
Re: Muse Spark 1.3
#245What a day. OpenAI is behind basically all major competitors - at least for a some amount of time.
I highly doubt it's behind in practice, except for Anthropic
Re: Muse Spark 1.3
#246Very keen to try this after using Claude Code over the last few months. Should I just point Claude Code to Muse Spark endpoint (because I'm familiar with Code)? What do people think of Muse Code or other coding agent harnesses?
Just try opencode, it comes with 1.3 contributor free.
Well thats very interesting. Thank you.
Will be interesting to see how hard/easy it is to translate my Claude skills, loop design, etc to the new harness.
This kind of raises another question to me regarding the coding benchmarks, how much of it is model versus harness?
Re: Muse Spark 1.3
#247Is the fact that everybody almost catches up with the frontier a sign that we are entering a new region of sigmoid curve?
I think it means that we should be aiming further ahead
Re: Muse Spark 1.3
#248llm -m meta-ai/muse-spark-1.3 "Generate an SVG of a pelican riding a bicycle" https://tools.simonwillison.net/markdown-svg-renderer?url=ht... 4.2266 cents, 38 seconds. For comparison here's Muse Spark 1.2, which animated it without me asking it to: https://tools.simonwillison.net/markdown-svg-renderer?url=ht... The 1.3 one is definitely better - better bicycle frame, better wing, better pelican hat. UPDATE: Here's an…
Is there any point anymore regarding this svg test? I would not be surprised if in the training they're fine tuned for this task too
It also works as extremely effective engagement farming, for lack of a better phrase
Re: Muse Spark 1.3
#249Earlier quoted context omitted.
Anthropic/Amodei have been the most alarmist about model safety, so multiple things can be true. A lot of tech companies avoided scrutiny by sending bribes to Trump (naked corruption is bad, I'd rather nobody do that), Anthropic didn't...so, combined with their fear-mongering about the danger of Mythos and open models (which seems aimed at regulatory capture) and the lack of bribes flowing to the Trump administration…
I don’t see how you can look at what happened with hugging face and keep up the facade of anyone being alarmist or faking it.
Security vulnerability capability is not the only thing they're scare-mongering about. They're the biggest purveyors of the, "We think the little guy in the computer who is made of algebra might be a real live boy and he might want to kill all of humanity when he grows up," line of alarmism.
Re: Muse Spark 1.3
#250I had no idea Meta has a coding agent harness. Does anyone have experience with it and can comment? The 1.3 contributor prices look very attractive. I'll probably start using their API if performance is good and the API is reliable with decent rate limits.
You should use their harness. They trained it on multiple harnesses but have specifically optimized it for their harness. Cline also did an independent experiment w spark 1.2 where using the native harness makes it use fewer tokens / turns to accomplish tasks
Any more info on this?