Hacker News new | past | comments | ask | show | jobs | submit login

Almost every single major benchmark, and yes progress is incremental but it adds up, this has always been the case



We were talking about linear improvements and I have yet to see it


check the benchmarks or make one of your own


I checked the BlEU-Score and Perplexity of popular models and both have stagnated around 2021. As a disclaimer this was a cursory check and I didn't dive into the details of how individuals scores were evaluated.


on what benchmarks? pretty much every major one is linear improvement




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: