Re:Muse Spark Open
by drivebyhooting on Thursday October 15, 2026 @03:39PM
(#50109146)
Astra still outperforms Argon for me. And with a lot more quota too.
I hope Google can catch up to OpenAI. The more competition the better.
Re:Muse Spark Open
by theturtletalks on Thursday October 15, 2026 @03:15PM
(#50108792)
I’m talking from experience. I’m run a software factory building open source alternatives and Argon is the worst model. Wrecked multiple codebases. But every use case is different. If you’ve found success in yours, use it.
I’m surprised it had time to “wreck multiple codebases” in the few days it’s been out
Re:Muse Spark Open
by benhurmarcel on Friday October 16, 2026 @04:07AM
(#50115542)
What you don't one-shot rewrite your entire codebase every time a model comes out?
Re:Muse Spark Open
by theturtletalks on Friday October 16, 2026 @10:32AM
(#50118840)
I use it in my software factory and it made the applications worse. I didn’t push the changes. I just reverted them.
Argon is tied for first at worst.
> Google is one of many funded models that were close to SOTA, but we realized it’s benchmaxxed.
Who is "we"? Google is the least benchmaxxed.