Our readingWhat is a korrent?
Models will not learn to write maintainable code from today’s benchmarks, because the cost of bad architecture cannot be measured by running the unit tests — it arrives three to six months later.
Drawn from what Dex Horthy said
What these subjects mean
design How things should be made and judged: what makes a design good, who should do the designing, and what an interface is for.
writing Prose as thinking: writing well, writing by hand while a model offers to do it, and who will still be able to.
software quality Whether a program is any good and how anyone would know: tests, review, debt, and what a suite cannot cover.
Mental modelFeedback loops
On the topicWhat are tests for, and how much testing is enough?under our view: Tests an agent wrote cannot be trusted on their own, so a person still has to check