Hacker News

points by speedping 3 days ago | 0 comments

ERNIE feels old, like BERT. They either need a rebrand or fully embrace retro-dawn-of-ML vibes

BERT models are still amazing for what they do. Even the latest JEV/KEV/SEV/BEV/REV/TREV models can't beat a well-trained BERT.

[–] endymi0n 2 days ago

hehe, so much in a name... just today I told Claude off for recommending me a BERT model for voice identification and it told me it was actually SOTA 2025!

https://arxiv.org/html/2510.04213v1

[–] throwaw12 3 days ago

do you have examples of open weight BERT models from hugging face which are trained for specific use cases?

[–] rockinghigh 2 days ago

For these small models, you would fine tune them on your use case. https://huggingface.co/transformers/v4.8.2/training.html

[–] rwmj 3 days ago

Very old .. https://en.wikipedia.org/wiki/Premium_Bonds#ERNIE

[–] josh-wrale 3 days ago

Bert and Ernie. Ring a bell? Sesame Street

[–] Oarch 2 days ago

I'd like to see Big Bird drop his weights next

[–] josh-wrale 2 days ago

I predict it will be ELMO with hands to the sky

[–] cubefox 2 days ago

https://en.wikipedia.org/wiki/ELMo

[–] kotaKat 2 days ago

... My mind wandered to the old Xbox font exploits. Bert & Ernie Reloaded!

http://archiv.sega-dc.de/phoenix.maxconsole.net/docs/bertern...