cheaty
@cheatyyyy
24, sde @ stealth startup, performative nerd
- Jesus Christ you should use Muse Spark 1.2 as your default cheap model it is so SO fast, I'm averaging 200 TPS in general use, not going to use anything but xhigh for early impressions but man it is so snappy and responsive in pi Meta's compute shining here as expected, excitedMeta Muse Spark 1.2 pricing is cheaper than DeepSeek v4 Flash! You get 95% off~ roughly for letting your data be used for training. (DeepSeek also uses your data for training on their official API)
- long context is a harness problem and not a model problem insane work by @PrimeIntellect, thank you for the open source release 🫡Replying to @PrimeIntellectWe recommend using Prime Agent for both day-to-day work and standalone evals. We find strong downstream performance gains for open and closed frontier models using Prime Agent on standard long-context and long-horizon tasks, despite modern models not being trained around Prime
- Meta Muse Spark 1.2 pricing is cheaper than DeepSeek v4 Flash! You get 95% off~ roughly for letting your data be used for training. (DeepSeek also uses your data for training on their official API)Meta’s Muse Spark 1.2 is out with Muse Code, a new coding harness by Meta
- Muse Code is a Rust binary, similar to Grok Build. (also uses ratatui)Meta Muse Spark 1.2 pricing! You get 95% off~ roughly for letting your data be used for training.
