Monthly episodes discussing this topic, 2025-05 to 2025-10.

Not enough disagreement in the transcripts to form camps. These are the positions taken by people with demonstrated expertise on this topic first, then by how many people heard them on it, then by VoiceRank.

Amjad Masadguest87

Amjad Masad contends that reinforcement learning is the primary breakthrough that enabled long-horizon reasoning in modern language models.

“I think it's RL I think it's uh reinforcement learning.”

a16z · Oct 2025 · 1 episode · 46K views on this topic

Positions are extracted from transcripts by a model and may misattribute who said what. Every quote links to the episode it came from.