[🖥️ Slides] [📓 Jupyter Notebook] In a keynote at the Workshop on Computational Models in Social Epistemology 2023, organised by the RUB Research Group on Reasoning, Rationality and Science as part of the DFG network “Simulations of Scientific Inquiry”, we’ve reviewed and critically reflected on the emergent field of LLM-based multi-agent simul... Read more 11 Dec 2023 - less than 1 minute read
[📝 Paper 1] [📝 Paper 2] [📈 Data at WandB] Large language models (LLMs) like ChatGPT are about to revolutionize our linguistic practices. These systems are highly proficient in writing, processing, and analysing texts. ChatGPT, for example, can pass an MBA exam, write a business plan, improve code, argue fervently for (or against) a policy pro... Read more 09 Feb 2023 - 3 minute read
[📝 Paper] [📓 Jupyter notebooks] [🐍 Python library] Argumentation (the process of producing arguments and responding to those put forward by others) can influence opinion dynamics in artificial agents: from previous research we already know that argumentation can be conducive to agreement among artificial agents, and that the effect size depend... Read more 02 Feb 2022 - 2 minute read
[📝 Paper] Doxastic conservativism is the idea that, when forced to change one’s beliefs (e.g., because of novel evidence), one should retain as many previously held beliefs as possible. Yet, is this really a sensible policy? Or, couldn’t it makes sense to revise one’s position more drastically (than strictly required) in order to attain an over... Read more 17 Jan 2022 - 3 minute read
[📝 Paper] [💻 Code] In “Making Reflective Equilibrium Precise: A Formal Model,” co-authored with Claus Beisbart and Georg Brun, we present a formal, computational model of reflective equilibrium (RE). The basic thrust is to explicate the method of RE as a process of step-wise “belief” revision that modifies – alternately – an agent’s current co... Read more 12 Jan 2022 - less than 1 minute read