# hi!! I'm Kamilė Lukošiūtė^[ ![[L1003459.jpg | 200]]]. I live in the Bay Area. I'm opinionated about coffee, fabrics, hiking routes, and large language model evaluations. A few years ago, I was also opinionated about modelling kilonovae and accelerating discovery in astrophysics through machine learning. Right now, I'm thinking about how we can improve the epistemics of LLM evaluation. ### things to read on this page - [[You need to be spending more money on evals]]: On over-generalisation in LLM evaluations - [[Maybe don't give language models standardized tests]]: On misleading LLM evaluations - [[American Character]]: On the best things about America ### previously... - (2022-2023) I was a resident researcher at Anthropic, where I worked on scalable oversight and evaluations. - (2021-2022) I was a PhD in machine learning for theoretical physics but dropped out to help to make AI's safe. - (2018-2021) During my bachelor's and master's in physics, I worked on [making astrophysics research easier with ML](https://arxiv.org/abs/2204.00285). ### recommendations People sometimes give book/blog/movie recommendations on their websites - either sincerely or because such lists represent who they are. I find that media is too personal to recommend like this, and no set will ever sum up my identity. I can, however, wholeheartedly recommend the following: - go outside - build meaningful relationships - seek truth ### contact! [[CV.pdf |CV/Resume]] [twitter](https://twitter.com/kamilelukosiute) Email me at `[lastnamefirstname]@gmail.com` (sans diacritics). I like getting emails!