LLMs are 'bags of contextually activated circuits, heuristics and algorithms'

xuanalogue · x · 2026-09-27

In a thread on mechanistic metaphors for LLMs, xuanalogue proposes thinking of models as 'bags of contextually activated circuits, heuristics, and algorithms.' He argues that understanding them only at the training level (next-token prediction + RL) is useful but punts on learned internal structure—and that this metaphor explains both LLM competencies and their failures despite massive training.

Related event: LLMs as Bags of Contextually Activated Heuristics(3 posts)→

Original post →

More from Research

Research channel →