alt Hacker News> I also think this "paper then code" approach is now obsolete. The modern way, in AI-assisted workflows
To call the approach obsolete and refer to a "modern way" to use an LLM seems like a stretch when critiquing the approach used by a frontier lab a month ago.
Shrug. It's how I do my research now. There were too many mathematical errors when I had agents writing LaTeX directly, even with adversarial reviews, so now I only read stuff that's been formalized, with whatever kinks worked out along the way.