Programmer Humor

gherkin tests?

We recently had an example of this. See Bun vs Zig. Even if your LLM doesn't have meaningless tests and assertions, those will not have 100% coverage on any non-trivial code base.

It just means he is not doing anything important, in other words he doesnt have any specific thing in mind and it doesn't matter if it works exactly right or not.

It looks like it's working and for some people that's enough.

So what exactly is he wrong about in here? Are you people running your agents without guardrails and constraints?

Tests are input output, the shape comes from how you get from the input to the output.

Why am I not surprised that he is a big proponent of AI coding considering his background ...

"Look idiots, I have the machine that confidently lies ask itself if it did good. If the confident lie machine lies to itself and the machine being lied to lies again by saying to me that the first lying machine did not lie... Then I have 7 more lie machines do the same thing in sequence. So in the end, the only way I could fail is if all these amoral lying machines that lie, somehow ALL lied to each other, and then to me - which according to the lying machine, is impossible."

Does he think a single AI model, perhaps in the same instance, will start to get better when put through "hard testing" in his "gauntlet"?

One thing I do love about the LLM era is that people get forced to be way more pendantic when it comes to code, and that's a win for everyone.

... Well admist the enormous losses LLM brings

Is this an "I am a very stable genius" confession for sloperators, or is there something I'm missing? 🤔

Look, I don't care what you do with your gherkin, Uncle Bob, but you do it in private, OK?

The only thing I got out of this is craving a pickle.