Hacker News Reader

They work on research problems you can define a clear solution criteria for.

The kinds of business software I work on don't have those characteristics. If I needed something like a utils library, I think I could easily have Claude write the whole thing and not read the code.

View on HN

What puzzles me is this: research means that we are exploring something that has not done before, yet using Claude to generate code means slicing and dicing what has been done many times before. So, I'm not sure how to make sense of both at the same time: Anthropic is pushing the boundary of AI, yet all the knowledge and engineering in form of code can be generated from the previous work?

How I interpreted their thoughts on "loops" and "graphs" etc, is that they 1. have unlimited token allowances, and 2. are working on problems where the solution itself can be described by code.

It reminds me of property based testing. I really liked the idea when I heard about it, but most of what I work on does not tend to behave in a way that can be easily described mathematically like that.

Maybe I'm just not clever enough to do it.

As always, the essential skill in engineering is not providing the right answer it's about asking the right questions.

Reply on news.ycombinator.com