Models spontaneously run internal expert debates when solving hard problems, nobody designed it
profjamesevans · x · 2026-10-27
Amir Zohrenejad observes that when models tackle hard problems, an internal debate plays out between the "experts" inside the model — a mechanism nobody explicitly designed; training simply made it the default behavior. The observation echoes James Evans' research on reasoning models generating "societies of thought": LLMs simulate a society of perspectives rather than a single brain.
More from Models
- Smaug Humanizer goes open-weights: de-AI-slop your text, built on Gemma — bindureddy · 2026-10-27
- Model Lineups Defended: 'One Benchmark Score Can't Capture a Model's Utility' — craigsdennis · 2026-10-27
- Claude research model claims to refute Exponential Time Hypothesis with 14M-token autonomous run — scaling01 · 2026-10-27
- Kimi K3 on AMD MI355X: +38% agentic throughput, +86% peak vs NVIDIA B300 — YouJiacheng · 2026-10-27
- Gemini turns out notably negative on Anthropic's IPO, ex-OpenAI exec jokes — Miles_Brundage · 2026-10-27
- MiniMax M3.1 Flash beats Claude Opus 5.5 on agentic automation at ~27x lower cost — togethercompute · 2026-10-27