Reflection AI Unveils Beam: 501B-Parameter Open Model With 23B Active, Weights Coming This Month
YugeTen · x · 2026-10-06
Reflection AI announced Beam, a highly efficient agentic open model with 501B total parameters and 23B active. Trained end-to-end from scratch, it claims frontier reasoning efficiency and advances the Western open frontier on coding and agentic tasks, with full weights releasing this month. The RL science team lead says clean RL at scale bakes in token efficiency and shows no capability plateaus.
More from Models
- Jeremy Howard: Google shipped the best model ever made; OpenAI its worst, same day — hugobowne · 2026-11-20
- Polymarket puts 83% odds on Google having the best AI model by year-end — Polymarket · 2026-11-20
- One year later, model naming is still a mess: the gpt-5.1-codex-max anniversary — heyneighbor · 2026-11-20
- Developer slams Grok models as 'garbage', shares coding agent's repetitive trial-and-error log — feregri_no · 2026-11-20
- Drex Router cuts small-game build cost to $1.26 vs $13.44 on Claude Opus alone — testingcatalog · 2026-11-20
- OpenAI slammed for AI slop: 'Just hire photographers to RLHF imagegen for a day' — flowersslop · 2026-11-20