Neuroscientist Kording shares an explainer of how LLMs work for an informed general audience
KordingLab · x · 2026-08-26
Konrad Kording notes there is still no proper explanation of how LLMs actually work targeted at an informed general audience, so he and Tim put together an explainer thread inspired by CIFAR's LMB discussions. It will be part of an upcoming manuscript and was optimized with Brett Mensh; feedback welcome.
The core framing: everyday language wherever possible, technical terms marked in purple. The key distinction is between the component that makes answers (blue, "inference") and the component that improves answers (red, "training").
More from Research
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- One tiny word changes the conversation: how LLMs pick up on 'just' — StellaLisy · 2026-10-16
- SEAR: first large-scale controlled study of self-evolving robot agents, 7 LLMs, 330 tasks — xiye_nlp · 2026-10-16
- After Claude-assisted elliptic curve records fell, EC Rank challenge opens 156 record slots — Jsevillamol · 2026-10-16
- Oxford neuroscientist swaps fetal MRI for ultrasound + ML models — AnnaCiaunica · 2026-10-16
- vegaml ships a full open-source toolbelt: cascaded inference, calibration, MCP server — kalyan_kpl · 2026-10-16