19h agoMicrosoft AI's Luca Soldaini acknowledged a terminology correction for the SWE-bench benchmark raised by academic Ofir PressSoldaini previously co-led the OLMo open LLM project.SentimentSentimentPos100%Neg0%Users thank the researcher for acknowledging the correct SWE-Bench name because the polite correction shows respect and accuracy in AI benchmark discussions.1 comment with sentiment. View comments.