Have we made a unicorn? Continuous SVG-pelican style benchmarkhavewemadeaunicorn.com·2 pts·curioussquirrel·1
How well do LLMs work outside English? We tested 8 models in 8 languages [pdf]info.rws.com·3 pts·curioussquirrel·5
LLMs are getting better at character-level text manipulationblog.burkert.me·138 pts·curioussquirrel·108