LLM Programming and Theory Building
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Kevin Lynagh describes trying to rewrite his Tasktron workflow harness with LLM coding agents (Astra 6, Opus 5.5, Sol 6.1) over several weeks and failing to get concise, well-factored code, since the models kept adding overlapping concepts, scattering mutable state, and writing overly specific tests.