Justin Miller

@olgarithmic.bsky.social and I had a paper out, and I'd love to share it with #NAFOfellas here. We looked at how in 2022-2023, despite the increasingly deteriorating state of X and changes to the algorithm, #NAFO explored it through play and used in their resistance. spir.aoir.org/ojs/index.ph...

Human-interpretable clustering of short text using large language models | Royal Society Open Science Clustering short text is a difficult problem, owing to the low word co-occurrence between short text documents. This work shows that large language models (LLMs) can overcome the limitations of tradit...

My first ever paper, in Royal Society Open Science shows how large language models can cluster short text more effectively than traditional methods—letting researchers condense massive social media corpora into easy-to-digest groups.
Check it out: royalsocietypublishing.org/doi/10.1098/...