Machine Readable 

Halcyon believes that building in public is an important part not just of demonstrating technology capabilities, but of developing them as well. We have been sharing elements of our work in public, but most of our efforts to date have been visible only behind a login.

Last week our staff engineer Will Hakim wrote about his learnings from building with artificial intelligence and large language models. One of his most important observations is that AI applications thrive not just based on technology, but from (in his words) understanding a customer’s workflow and fitting AI into it.

Last week, New York City hosted two events which wear out the shoe leather (and sometimes the patience) of New Yorkers and visitors alike: the United Nations General Assembly (UNGA), and Climate Week NYC.

When Bruce and I were initially discussing what Halcyon would become, the question of what data and information to prefer in our ingestion processes, at first, was important. Perhaps I did not help matters much when Bruce asked me “what information do you want?” and I responded “all of it.”