Radical Numerics Profile
Radical Numerics

@RadicalNumerics

Followers
1K
Following
15
Media
5
Statuses
8

San Francisco & Tokyo
Joined May 2025
Don't wanna be here? Send us removal request.
@garykbrixi
Garyk Brixi
2 months
Excited to share Phalanx, our new layer for sequence modeling! Each block communicates with its neighbor, like the shield cover of a neighboring hoplite. Phalanx can replace sliding window attention and trains faster than optimized baselines while maintaining quality.
@RadicalNumerics
Radical Numerics
2 months
Sliding window attention (SWA) is powering frontier hybrid models for efficiency. Is there something better? Introducing Phalanx, a faster and better quality drop-in replacement for sliding window attention (SWA). Phalanx is a new family of hardware and numerics-aware windowed
2
9
50
@RadicalNumerics
Radical Numerics
2 months
More on Phalanx and our research kernel library: Blog: https://t.co/NzyyFuSIKr Code: https://t.co/kHosQhyHSD Report: https://t.co/iVLETD2AYx
1
2
13
@RadicalNumerics
Radical Numerics
2 months
Sliding window attention (SWA) is powering frontier hybrid models for efficiency. Is there something better? Introducing Phalanx, a faster and better quality drop-in replacement for sliding window attention (SWA). Phalanx is a new family of hardware and numerics-aware windowed
12
52
205
@MichaelPoli6
Michael Poli
2 months
We just released the largest open-source diffusion language model (RND1). RND1 is important to me on a personal level: it symbolizes our commitment to open-source exploration of radically different designs for AI at scale — training objectives, architectures, domains. There is
@RadicalNumerics
Radical Numerics
2 months
Introducing RND1, the most powerful base diffusion language model (DLM) to date. RND1 (Radical Numerics Diffusion) is an experimental DLM with 30B params (3B active) with a sparse MoE architecture. We are making it open source, releasing weights, training details, and code to
9
40
330
@RadicalNumerics
Radical Numerics
2 months
Thank you @nebiusai, @PrimeIntellect, @LambdaAPI for the compute resources and support
5
0
70
@RadicalNumerics
Radical Numerics
2 months
We’re also hiring aggressively. Reach out if you’re interested in building automated research environments and agents. (AI researchers and SWEs, pre/mid/post training, architecture design, kernels, lots of backend system design, and automation) Our team is behind the tech for
16
5
112
@RadicalNumerics
Radical Numerics
2 months
1
5
86
@RadicalNumerics
Radical Numerics
2 months
Introducing RND1, the most powerful base diffusion language model (DLM) to date. RND1 (Radical Numerics Diffusion) is an experimental DLM with 30B params (3B active) with a sparse MoE architecture. We are making it open source, releasing weights, training details, and code to
103
256
1K