Loading activity…
@_ghorbani
Head of Post-Training at @Reflection_ai. Formerly @OpenAI (High-Compute RL) and @GoogleBrain. PhD @stanford_ee.
AI
Amos’s paper targets rounding and cancellation errors in comparisons of nearly equal probability distributions.
AI
Reflection says Beam uses 23B active parameters and plans to publish its full weights later in October 2026.