Hacker News Reader

Google is using BERT for most/all search queries [1]. BERT is far smaller than Megatron (340M < 530B), but still "big" in a traditional sense (in the blog they say they are using TPUs for inference).

[1] https://blog.google/products/search/search-language-understa...

View on HN

Don't forget that Google is not stopping at BERT. I dunno if they used any of the T5s or Switch Transformers in production, but they've said that MUM (O(100b)?) is going to run for production search queries, and no one knows what 'Pathways' is (multimodal O(1000b) MoE?) that Jeff Dean has been enthusing about.

Interesting, though as you noted it's less than 1/1000th the size of the 530B model and according to the article is only used in about one in ten U.S.-based English-language searches, at least when that was written.

Reply on news.ycombinator.com