# Max Schwarzer

Markdown copy of https://realalpha.app/people/max-schwarzer/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

Real Alpha has cut one moment of Max Schwarzer (Member of Technical Staff, Anthropic) talking, from an interview on TBPN published Aug 7, 2025.

- Role: Member of Technical Staff, Anthropic
- About: Led OpenAI's post-training for o1 and o3, and helped develop its o1-preview reasoning model.
- On X: https://x.com/max_a_schwarzer

## What Max Schwarzer said

- [Post-training improvements made GPT-5 more reliable](https://realalpha.app/s/post-training-improvements-made-gpt-5-more-reliable/)
  TBPN · Aug 7, 2025 · 5 min
  > “And if you do that, all of a sudden, the model stops saying things that are false.” — Max Schwarzer · [3:12:01](https://realalpha.app/v/gaImbWPGgtU/?t=11521)

## The episode

- [OpenAI LIVE: Greg Brockman, Mark Chen & More](https://realalpha.app/v/gaImbWPGgtU/) · TBPN · Aug 7, 2025