Reflection AI unveils Beam: 501B-parameter open agentic model, weights this month
luke_drago_ · x · 2026-10-06
Reflection AI introduces Beam, a highly efficient agentic open model with 501B total and 23B active parameters. The company claims frontier reasoning efficiency and advances on the Western open frontier for coding and agentic tasks, trained end-to-end from scratch, with full weights releasing this month. Former OpenAI safety researcher Neil Chowdhury voiced excitement about pushing open-weight safety forward.
Related event: Reflection AI Debuts Beam, Its First Open-Weight 501B MoE Model(34 posts)→
More from Models
- Will OpenAI Merge Chat and Codex Quotas? Users Fear Tighter Basic Chat Limits — Iwantthegreatest · 2026-10-06
- Microsoft page reportedly confirms GPT-6 series uses Looped Transformers — teortaxesTex · 2026-10-06
- Amazon's ALoDLM: Token-Adaptive Looped Diffusion LMs Beat AR Baselines — amazon · 2026-10-06
- Looped LMs at Fixed Points: 3x Smaller KV Cache, 1.79x Faster Prefill — IFM · 2026-10-06
- Australia open-sources Matilda Jev, a 56.8ms decision model that skips text generation — Med1_Ai · 2026-10-06
- Codex politely pushes back on a user's hallucinated claims — "I'm also a journalist" — MikePFrank · 2026-10-06