Ian ArawjoLLM Wrapper Papers are Hurting HCI ResearchNaming the problem and deciding what to do about itJun 61Jun 61
Ian ArawjoNo, ChatGPT does not have seasonal affective disorderA Perilous Tale of Why We Check Assumptions Before Running Statistical TestsDec 12, 2023Dec 12, 2023
Ian ArawjoKicking the Leg Out From the Table: On Contrived Controls in HCI Systems ResearchConsider this table. This table has four legs. To run a controlled study on the user experience of this table, we kick out one of the legs.Oct 4, 2023Oct 4, 2023
Ian ArawjoEvaluate LLMs, right in your browser. Share your experiments with others.No installation or login requiredJul 5, 2023Jul 5, 2023
Ian ArawjoYou can now run OpenAI evals in ChainForgeWith the click of a buttonJun 16, 2023Jun 16, 2023
Ian ArawjoIntroducing ChainForge: A visual programming environment for prompt engineeringWhat prompt should I use? What model should I use? At what settings?May 23, 20232May 23, 20232
Ian ArawjoOn Notational Programming for Notebook EnvironmentsWhen we speak of “writing” code, we — almost always — imagine typing it. But will we always?Oct 15, 20211Oct 15, 20211
Ian ArawjoOn dehumanization, accountability abuse, and transformative justiceCW: abuse, conflict, violence, genocideApr 8, 2021Apr 8, 2021
Ian ArawjoinAn Injustice!CS for Racial Literacy: Teaching Race through Cultural AlgorithmsCan computing concepts help kids learn about race?Feb 15, 2021Feb 15, 2021
Ian ArawjoAI From the Very Beginning: Integrating AI Perspectives into an Intro UX CourseFive takeaways from our attempt to integrate an AI perspective into an intro UX course at Cornell University.Dec 29, 20201Dec 29, 20201