Microsoft researcher points out BERT was already called an LLM back in 2019
JFPuget · x · 2026-09-20
Microsoft researcher JFPuget reminds people that "LLM" isn't a new term — BERT and other large pretrained language models were already being called LLMs in 2019. He cites Lilian Weng's January 2019 blog post Generalized Language Models, which surveys the lineage from CoVe, ELMo and ULMFiT through GPT, BERT, GPT-2, and later T5, GPT-3, XLNet, BART and ELECTRA.
More from Research
- Pachter Lists More Flaws in Nucleus Ads: Implausible R² Matches, Mismatched Cohorts — lpachter · 2026-09-20
- Biologist Debunks Nucleus Claim That Embryo Screening Boosts IQ by 10.8 Points — lpachter · 2026-09-20
- Paper Nucleus Cites for IQ Screening Explicitly Calls the Number an Upper Bound — lpachter · 2026-09-20
- A week-long calendar benchmark across 5 cultural calendars became this researcher's highest-rated paper (8/7/7) — cneuralnetwork · 2026-09-20
- ActionPiece rethinks action tokenization for VLA models, hits 94.8% on LIBERO — burny_tech · 2026-09-20
- Zero-token chatbot: picks from 400 pre-written replies, ~100x cheaper — dwarfLevi · 2026-09-20