Дени Марс

[Дени Марс @DenMarsOfficial]

@MiniMax_AI @opencode ❤️

[Дени Марс @DenMarsOfficial]

@Zai_org Half my tokens were gone, and not a single one of 10 prompts finished. Every task crashed halfway through with random errors. All I've been doing is filing support tickets. This product is still way too raw.

[Дени Марс @DenMarsOfficial]

@opencode MiniMax M3 (3x usage) forever ❤️

[Дени Марс @DenMarsOfficial]

@DeRonin_ I am disappointed that the MiniMax M3 is not on the list 😞

[Дени Марс @DenMarsOfficial]

@israfill Long life to you and prosperity

[Дени Марс @DenMarsOfficial]

@LuminaXspace What's the point of speed if the model is dumb as a rock? Especially when there are other models that are only slightly more expensive—or sometimes even cheaper.

[Дени Марс @DenMarsOfficial]

@jietang Work for a day, wait a week. Work another day, wait another week. Work half a day, wait a month. That's the whole subscription. What features? Your model burns through tokens so fast it feels like it's charging me even when I'm not using it.

[Дени Марс @DenMarsOfficial]

@bridgebench Even at your brother's wedding, you can't help but think about AI, bro?)))

[Дени Марс @DenMarsOfficial]

@WhaleInsider China is a powerhouse

[Дени Марс @DenMarsOfficial]

@ornith_ @opencode, any chance I could test out the Go plan?

[Дени Марс @DenMarsOfficial]

@ornith_ Code generation is the least interesting part. The real test is how well a model debugs existing code.

Most of the job is fixing bugs, refactoring, and navigating large codebases—not writing another Minecraft clone.

[Дени Марс @DenMarsOfficial]

@adahstwt The one that Opencode gives away for free

[Дени Марс @DenMarsOfficial]

@nutlope GLM 5.2 is only cheaper than Opus 4.8 on paper. In reality, it burns through so many tokens that it ends up costing about the same as Opus — maybe even more.

[Дени Марс @DenMarsOfficial]

@jun_song GLM 5.2 burns through tokens like crazy. I used 64,490,004 tokens in just 2 days, and now I have to wait 5 days for my quota to reset. In practice, it's not any cheaper than other models because it consumes tokens at an insane rate.

[Дени Марс @DenMarsOfficial]

@testerlabor The key isn't the amount of training data, it's the quality. If you're training on garbage code, then even trillions of parameters are basically useless.

[Дени Марс @DenMarsOfficial]

@opencode God bless OpenCode and Minimax for that 3x usage boost. 🙏

[Дени Марс @DenMarsOfficial]

@IntuitMachine Nothing to impede progress.

[Дени Марс @DenMarsOfficial]

@EnglishShibby A single MMO. The shit is empty. with killing for the sake of killing. Play Skyrim - it's the game of the century.

[Дени Марс @DenMarsOfficial]

@MiniMax_AI @jayair @opencode Huge thanks for the x3 usage increase in OpenCode ❤️

[Дени Марс @DenMarsOfficial]

@jenzhuscott MiniMax ❤️