Chollet：基础 LLM 与现代 LRM 的关键区别是从传导转向归纳
Francois Chollet 指出，基础 LLM（2024 年及更早）与现代 LRM 的关键区别不在于符号工具使用，而在于从传导范式（直接直觉出查询的答案）转向归纳范式（直觉出产生答案的程序或指令）。
The critical distinction between base LLMs (2024 and earlier) and modern LRMs is not symbolic tool use. It's the switch from a transductive paradigm (intuit the answer to the query) to an inductive paradigm (intuit the program/instructions that produce the answer to the query).
They're trained to be inductive, and they perform test-time induction, i.e. test-time prediction of a NL program / reasoning chain. This unlocks entirely new capabilities -- in particular fluid intelligence. Base LLMs, to this day, have ~0 fluid intelligence. LRMs have substantial levels of fluid intelligence.
The performance of LLMs on ARC 1 (a benchmark from 2019) remains ~10-15% today. Scaling them up by a factor ~100,000x got them from 0% to 10%. Meanwhile LRMs the same size or smaller saturated ARC 1 in 2025.
来源：fchollet · x.com