Everything I built with Claude Artifacts this week

Re:Everything I built with Claude Artifacts this week by majormajor on Wednesday October 23, 2024 @07:50PM (#41930425)

I would've expected an answer involving "an exhaustive suite of test cases still passed" - "it looks right" is a low bar for any complex software project these days.

It's the long, long, long tail of edge cases - not just porting them, but even identifying them to test - that slow or doom most real-world human rewrites, after all.

[ Parent | on HN ]

Re:Everything I built with Claude Artifacts this week by josephg on Wednesday October 23, 2024 @08:05PM (#41930507)

True - but you can ask the chatbot to write a test suite too.

[ Parent | on HN ]

Re:Everything I built with Claude Artifacts this week by what on Wednesday October 23, 2024 @10:12PM (#41931245)

This doesn’t really make sense? If I can’t trust the code it writes, why should I trust that it can write a comprehensive test suite?

[ Parent | on HN ]

Re:Everything I built with Claude Artifacts this week by simonw on Wednesday October 23, 2024 @10:20PM (#41931287)

Because you can read the test suite to check what it's testing, then break the implementation and run the tests and check they fail, then break a test and run them and check that fails too.

You have to review the code these thing write for you, just like code from any other collaborator.

[ Parent | on HN ]

Re:Everything I built with Claude Artifacts this week by josephg on Wednesday October 23, 2024 @10:54PM (#41931470)

Because the bugs in its code and the bugs in its test suites usually don't line up and cancel each other out.

[ Parent | on HN ]