Intelligence with Everyone: RL @ MiniMax, with Olive Song, from AIE NYC & Inference by Turing Post

Olive Song from MiniMax shares how her team trains the M series frontier open-weight models using reinforcement learning, tight product feedback loops, and systematic environment perturbations. This crossover episode weaves together her AI Engineer Conference talk and an in-depth interview from the Inference podcast. Listeners will learn about interleaved thinking for long-horizon agentic tasks, fighting reward hacking, and why they moved RL training to FP32 precision. Olive also offers a candid look at debugging real-world LLM failures and how MiniMax uses AI agents to track the fast-moving AI landscape.

Nathan uses Granola to uncover blind spots in conversations and AI research. Try it at ⁠granola.ai/tcr⁠ (granola.ai/tcr) with code TCR — and if you’re already using it, test his blind spot recipe here: ⁠bit.ly/granolablindspot⁠ (bit.ly/granolablindspot)

LINKS:

Conference Talk (AI Engineer, Dec 2025) – youtube.com/watch?v=lY1iFbDPRlw
Interview (Turing Post, Jan 2026) – youtube.com/watch?v=GkUMqWeHn40

Sponsors:

Claude:

Claude is the AI collaborator that understands your entire workflow, from drafting and research to coding and complex problem-solving. Start tackling bigger problems with Claude and unlock Claude Pro’s full capabilities at claude.ai/tcr

Tasklet:

Tasklet is an AI agent that automates your work 24/7; just describe what you want in plain English and it gets the job done. Try it for free and use code COGREV for 50% off your first month at tasklet.ai

CHAPTERS:

() About the Episode

() Minimax M2 presentation (Part 1)

() Sponsors: Claude | Tasklet

() Minimax M2 presentation (Part 2)

() Research life and culture

() Alignment, safety and feedback

() Long-horizon coding agents

() Open models and evaluation

() M2.2 and researcher goals

() Continual learning and AGI

() Closing musical summary