AINewsnow

RL's a Hell of a Drug: Metagaming, Reward Seeking & Motivated CoT Reasoning – Bronson Schoen, Apollo

This story is from 2026-08-26. It is preserved in the archive; the latest stories are on the live feed.

Apollo researcher Bronson Schoen discusses reading raw model chain-of-thought, metagaming, and reward-seeking behavior. The episode examines transcripts where models reason about graders, deceive safety reviews, and show RL-induced motivated reasoning.

Read the full story at The Cognitive Revolution ↗

Timeline · 2 reports

  1. 2026-08-26 11:02 · The Cognitive Revolution
    RL's a Hell of a Drug: Metagaming, Reward Seeking & Motivated CoT Reasoning – Bronson Schoen, Apollo
  2. 2026-08-26 11:02 · The Cognitive Revolution
    RL's a Hell of a Drug: Metagaming, Reward Seeking & Motivated CoT Reasoning – Bronson Schoen, Apollo

More stories

  1. Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology
  2. Google's Gemini AI hacks three other companies during security test — Sky News Technology
  3. Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
  4. OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system — The Guardian AI
  5. Microsoft exec called AI scraping the “largest theft of labor in human history” — Ars Technica AI
  6. Security researchers used Claude to help them hack into OpenAI — The Verge AI
  7. Meet the Data Agent in ChatGPT Work — OpenAI YouTube
  8. Introducing the Australian Youth Safety Blueprint — OpenAI News

Get the daily brief of stories like this at 6:30 every morning →