Reflection AI unveils Beam: 501B-total/23B-active open model, RL run on 10.5K GB300 GPUs
AccBalanced · x · 2026-10-06
Reflection AI officially introduces Beam, an efficient agentic open model with 501B total and 23B active parameters (relayed by Ian Andrews):
- Claims frontier reasoning efficiency, advancing the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch; full weights to be released this month
- Its high-compute RL run generated over 100 million rollouts on 10.5K NVIDIA GB300 GPUs over 4 weeks of training — prompting the comment "training becomes inference"
More from Infra
- Nvidia down ~40% from October peak as Anthropic IPO pops 34% above expectations — The Verge AI · 2026-11-20
- Ion Stoica explains why complex AI workloads increasingly fit Ray's design — PyTorch · 2026-11-20
- GPU rents up, token prices down: inference providers' break-even load jumps 22%–75% in 5 months — AccBalanced · 2026-11-20
- Missing config file was throttling GPUDirect Storage — fix yields 3x reads, 9x writes — AccBalanced · 2026-11-20
- NVIDIA Dynamo cuts RL rollout bottlenecks with KV-aware routing and delta weight updates — NVIDIAAI · 2026-11-20
- Arm reaches the AI laptop: Surface Laptop Ultra runs 120B models locally — kimmonismus · 2026-11-20