Demo 01
LMCRep — AI Replaceability in Corpus Linguistics
An interactive dashboard exploring how well state-of-the-art large language models can replace human researchers across 50+ corpus linguistics tasks. Each task is scored along 13 dimensions — from execution determinism to interpretive judgement load — by seven frontier LLMs including Claude Opus 4.7, GPT-5.5, and Gemini 3.1 Pro. Visualise cross-model comparisons, ensemble scores, and research-area heatmaps to see where AI already substitutes human effort and where fundamental barriers remain.