# Reflection AI explains how it trained and evaluated Beam for safety

> Original title: Sharing more about how we trained and evaluated Beam, our first model, for safety: https://reflection.ai/blog/open-model-safety-lessons

- Source: Reflection
- Published: 2026-11-05T17:01:42.000Z
- Bad Influence: https://badinfluence.news/items/bc91ctpnx23zlclhmpm7mn48q
- Original: https://x.com/reflection_ai/status/2118388295629508712

## Summary

Reflection AI says it has published a blog post on how it trained and evaluated Beam, its first model, for safety. The company says it will release additional safety research, evaluations, and tools under Project Iris, its open AI safety initiative, in the coming weeks.

## Post

Sharing more about how we trained and evaluated Beam, our first model, for safety: https://reflection.ai/blog/open-model-safety-lessons

In the coming weeks, we'll release additional safety research, evaluations, and tools under Project Iris, Reflection's open AI safety initiative.

We are committed to prioritizing safety in every model we build—and sharing what we develop and learn so that researchers, developers, policymakers, and enterprises can build on our work, advancing safety across the broader AI ecosystem.